Paper Citation Record · LEDGER

ZeroSearch: Incentivize the Search Capability of LLMs without Searching

As of 10 August 2026, this Paper Citation Record lists 49 of 49 outbound references and 64 inbound Pith citation observations for arXiv:2505.04588.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2505.04588 v3

Coverage vector

measured 49 of 49 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-22T16:05:04.715678Z

measured 113 of 113 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+00:00

measured 64 of 64 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:42:30.760995Z

measured 1 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: pith, observed 2026-08-05T02:28:24.338817Z

Reference resolution

49 of 49 outbound references displayed

verified exact38
verified fuzzy7
unresolved4
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

0
pith, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation 0ed22e2a-7a87-4995-a4d4-fb087f4355d0 · outbound

This paper cites an unresolved cited work.

ZeroSearch: Incentivize the Search Capability of LLMs without Searching Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-05-22T16:06:46.521909Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b3e0558a-fb04-49e5-b3dc-0261cad3e012 · outbound

This paper cites Attributed Question Answering: Evaluation and Modeling for Attributed Large Language Models.

ZeroSearch: Incentivize the Search Capability of LLMs without Searching Attributed Question Answering: Evaluation and Modeling for Attributed Large Language Models

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-22T16:06:46.008263Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation fc1a83de-39c9-4bd2-8f66-1bb346121f33 · outbound

This paper cites PaLM: Scaling Language Modeling with Pathways.

ZeroSearch: Incentivize the Search Capability of LLMs without Searching PaLM: Scaling Language Modeling with Pathways

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-22T16:06:46.002126Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e2108120-e918-49c2-aef3-21bdf03a2d61 · outbound

This paper cites The Llama 3 Herd of Models.

ZeroSearch: Incentivize the Search Capability of LLMs without Searching The Llama 3 Herd of Models

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-05-22T16:06:45.945313Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation daf9d241-e315-4d5f-a07d-5be4ab74a255 · outbound

This paper cites AirRAG: Autonomous Strategic Planning and Reasoning Steer Retrieval Augmented Generation.

ZeroSearch: Incentivize the Search Capability of LLMs without Searching AirRAG: Autonomous Strategic Planning and Reasoning Steer Retrieval Augmented Generation

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-22T16:06:45.871947Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 118043ca-bc29-4d0d-a07e-4ca7552b19c4 · outbound

This paper cites RARR: Researching and Revising What Language Models Say, Using Language Models.

ZeroSearch: Incentivize the Search Capability of LLMs without Searching RARR: Researching and Revising What Language Models Say, Using Language Models

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-22T16:06:46.036250Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 04cfbf3d-48cb-4c16-bd2a-32fcc5b7d7ef · outbound

This paper cites Self-Adaptive Gamma Context-Aware SSM-based Model for Metal Defect Detection.

ZeroSearch: Incentivize the Search Capability of LLMs without Searching Self-Adaptive Gamma Context-Aware SSM-based Model for Metal Defect Detection

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-22T16:06:45.917347Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d28a5430-c1ac-4c5e-8573-a16d1fc5e446 · outbound

This paper cites Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps.

ZeroSearch: Incentivize the Search Capability of LLMs without Searching Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-05-22T16:06:45.837584Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 94780eef-91aa-44b3-9c9f-18006e33b353 · outbound

This paper cites Hou and et al.

ZeroSearch: Incentivize the Search Capability of LLMs without Searching Hou and et al

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T16:06:46.503858Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ecbde63c-b3e4-46bb-87ea-b473e8a1299c · outbound

This paper cites MathPrompter: Mathematical Reasoning using Large Language Models.

ZeroSearch: Incentivize the Search Capability of LLMs without Searching MathPrompter: Mathematical Reasoning using Large Language Models

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-22T16:06:45.894985Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 88b13138-7e8c-4c15-aa85-363ba0b44bc7 · outbound

This paper cites Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity.

ZeroSearch: Incentivize the Search Capability of LLMs without Searching Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-22T16:06:45.991331Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b4e8efe0-8fd3-447e-9416-bcbe900edc2c · outbound

This paper cites an unresolved cited work.

ZeroSearch: Incentivize the Search Capability of LLMs without Searching Unresolved cited work

Reference 12

Resolution: unresolved; raw_fallback, observed 2026-05-22T16:06:46.506971Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 57606a0f-5ce6-4c1e-86f4-69a5ca8748fd · outbound

This paper cites RAG-Star: Enhancing Deliberative Reasoning with Retrieval Augmented Verification and Refinement.

ZeroSearch: Incentivize the Search Capability of LLMs without Searching RAG-Star: Enhancing Deliberative Reasoning with Retrieval Augmented Verification and Refinement

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-22T16:06:45.889296Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 56fe818b-eff3-4366-8fa8-a5ab4045d2de · outbound

This paper cites Enhancing LLM Reasoning with Reward-guided Tree Search.

ZeroSearch: Incentivize the Search Capability of LLMs without Searching Enhancing LLM Reasoning with Reward-guided Tree Search

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-22T16:06:45.978606Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 9e4f8f68-2215-44a9-820e-2c06d14a9293 · outbound

This paper cites Jiang, F.

ZeroSearch: Incentivize the Search Capability of LLMs without Searching Jiang, F

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T16:06:46.517680Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 15cb8905-537b-4941-9cde-da4944e50433 · outbound

This paper cites Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning.

ZeroSearch: Incentivize the Search Capability of LLMs without Searching Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-05-22T16:06:45.857185Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation eae25a6b-4832-4ec9-8cac-4022f3f16cf1 · outbound

This paper cites TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension.

ZeroSearch: Incentivize the Search Capability of LLMs without Searching TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-05-22T16:06:45.902609Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a4edba05-8aa9-4ca2-a615-ef8a9a364480 · outbound

This paper cites Kumar and et al.

ZeroSearch: Incentivize the Search Capability of LLMs without Searching Kumar and et al

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T16:06:46.513766Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7fa83612-8d22-4847-b208-117bf14f8551 · outbound

This paper cites The cat-bat map, the figure-eight knot, and the five orbifolds.

ZeroSearch: Incentivize the Search Capability of LLMs without Searching The cat-bat map, the figure-eight knot, and the five orbifolds

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-22T16:06:45.964714Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 53b9393f-0f96-4731-8160-a612152f4c5d · outbound

This paper cites Kwiatkowski, J.

ZeroSearch: Incentivize the Search Capability of LLMs without Searching Kwiatkowski, J

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T16:06:46.510097Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e9e61894-91b2-49ae-abb0-9c96ee73283d · outbound

This paper cites Lewkowycz, A.

ZeroSearch: Incentivize the Search Capability of LLMs without Searching Lewkowycz, A

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T16:06:46.541283Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a37fc1d9-9785-4e78-bdd4-d47b1624ac4e · outbound

This paper cites Search-o1: Agentic Search-Enhanced Large Reasoning Models.

ZeroSearch: Incentivize the Search Capability of LLMs without Searching Search-o1: Agentic Search-Enhanced Large Reasoning Models

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-05-22T16:06:45.851145Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d3546a73-0bf7-43d3-a7fc-fc2f07d15451 · outbound

This paper cites WebThinker: Empowering Large Reasoning Models with Deep Research Capability.

ZeroSearch: Incentivize the Search Capability of LLMs without Searching WebThinker: Empowering Large Reasoning Models with Deep Research Capability

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-05-22T16:06:46.046975Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6e915c3f-8ba6-4759-8de3-a8b8b166596a · outbound

This paper cites RetroLLM: Empowering Large Language Models to Retrieve Fine-grained Evidence within Generation.

ZeroSearch: Incentivize the Search Capability of LLMs without Searching RetroLLM: Empowering Large Language Models to Retrieve Fine-grained Evidence within Generation

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-05-22T16:06:46.052602Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 20a49fdd-6099-4342-b3cb-84ab51406479 · outbound

This paper cites Can We Further Elicit Reasoning in LLMs? Critic-Guided Planning with Retrieval-Augmentation for Solving Challenging Tasks.

ZeroSearch: Incentivize the Search Capability of LLMs without Searching Can We Further Elicit Reasoning in LLMs? Critic-Guided Planning with Retrieval-Augmentation for Solving Challenging Tasks

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-22T16:06:45.909112Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c8eaccbd-2f49-46a3-af06-b3db74d8f948 · outbound

This paper cites When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories.

ZeroSearch: Incentivize the Search Capability of LLMs without Searching When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-05-22T16:06:45.865737Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2e352b9b-a5b6-4e86-aefb-a608fa625ace · outbound

This paper cites Teaching language models to support answers with verified quotes.

ZeroSearch: Incentivize the Search Capability of LLMs without Searching Teaching language models to support answers with verified quotes

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-05-22T16:06:45.929246Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 40350ada-7b3d-46af-a72d-22cc6446deb2 · outbound

This paper cites Measuring and Narrowing the Compositionality Gap in Language Models.

ZeroSearch: Incentivize the Search Capability of LLMs without Searching Measuring and Narrowing the Compositionality Gap in Language Models

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-05-22T16:06:45.923648Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 08b0c24c-afe1-4f95-a02b-137390c3baa6 · outbound

This paper cites In-Context Retrieval-Augmented Language Models.

ZeroSearch: Incentivize the Search Capability of LLMs without Searching In-Context Retrieval-Augmented Language Models

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-05-22T16:06:45.985020Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 031031ae-629b-47f3-a859-97cae4a60cf7 · outbound

This paper cites Measuring Attribution in Natural Language Generation Models.

ZeroSearch: Incentivize the Search Capability of LLMs without Searching Measuring Attribution in Natural Language Generation Models

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-22T16:06:46.041523Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 67d26f8d-49dd-41e0-b1ca-ea516ada956a · outbound

This paper cites Proximal Policy Optimization Algorithms.

ZeroSearch: Incentivize the Search Capability of LLMs without Searching Proximal Policy Optimization Algorithms

Reference 31

Resolution: verified exact; local_arxiv, observed 2026-05-22T16:06:46.058115Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation cdfa4567-832d-444a-8a0a-19f19251f6e4 · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

ZeroSearch: Incentivize the Search Capability of LLMs without Searching DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-05-22T16:06:45.877971Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f77cde22-834b-4989-82f7-0570fd407320 · outbound

This paper cites REPLUG: Retrieval-Augmented Black-Box Language Models.

ZeroSearch: Incentivize the Search Capability of LLMs without Searching REPLUG: Retrieval-Augmented Black-Box Language Models

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-05-22T16:06:45.844247Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a6d116cf-06fb-4e49-9dd9-3f466ff9884e · outbound

This paper cites Retrieval Augmentation Reduces Hallucination in Conversation.

ZeroSearch: Incentivize the Search Capability of LLMs without Searching Retrieval Augmentation Reduces Hallucination in Conversation

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-05-22T16:06:45.935574Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation cce7010b-dbf3-4d25-9c26-4f2f1c6cfba9 · outbound

This paper cites R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning.

ZeroSearch: Incentivize the Search Capability of LLMs without Searching R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning

Reference 35

Resolution: verified exact; local_arxiv, observed 2026-05-22T16:06:45.950993Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8e92d8c3-fda0-49f0-881d-f15b7b83b2d5 · outbound

This paper cites Galactica: A Large Language Model for Science.

ZeroSearch: Incentivize the Search Capability of LLMs without Searching Galactica: A Large Language Model for Science

Reference 36

Resolution: verified exact; local_arxiv, observed 2026-05-22T16:06:46.025191Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation cf064b4b-ada2-4e87-a7da-aef48871542a · outbound

This paper cites Trivedi, N.

ZeroSearch: Incentivize the Search Capability of LLMs without Searching Trivedi, N

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T16:06:46.533639Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 406c6ac2-20fe-4deb-8845-57cb4bc38221 · outbound

This paper cites an unresolved cited work.

ZeroSearch: Incentivize the Search Capability of LLMs without Searching Unresolved cited work

Reference 38

Resolution: unresolved; raw_fallback, observed 2026-05-22T16:06:46.537542Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f9335210-c8ab-4c38-b471-6f8617752a2e · outbound

This paper cites Evaluating Mathematical Reasoning Beyond Accuracy.

ZeroSearch: Incentivize the Search Capability of LLMs without Searching Evaluating Mathematical Reasoning Beyond Accuracy

Reference 39

Resolution: verified exact; arxiv_id, observed 2026-05-22T16:06:46.064052Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c3b72591-3104-4a65-8a49-7f1ac7114e0c · outbound

This paper cites LPML: LLM-Prompting Markup Language for Mathematical Reasoning.

ZeroSearch: Incentivize the Search Capability of LLMs without Searching LPML: LLM-Prompting Markup Language for Mathematical Reasoning

Reference 40

Resolution: verified exact; arxiv_id, observed 2026-05-22T16:06:45.959021Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation fb050e05-cf9e-4512-a379-497430c95abd · outbound

This paper cites Qwen2.5 Technical Report.

ZeroSearch: Incentivize the Search Capability of LLMs without Searching Qwen2.5 Technical Report

Reference 41

Resolution: verified exact; local_arxiv, observed 2026-05-22T16:06:46.030639Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a0afbbf9-3877-4281-8ae6-07cbde7ce82e · outbound

This paper cites HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering.

ZeroSearch: Incentivize the Search Capability of LLMs without Searching HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering

Reference 42

Resolution: verified exact; local_arxiv, observed 2026-05-22T16:06:46.069057Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 45e4c17c-8699-4064-8669-a27db9fb026b · outbound

This paper cites Answering Questions by Meta-Reasoning over Multiple Chains of Thought.

ZeroSearch: Incentivize the Search Capability of LLMs without Searching Answering Questions by Meta-Reasoning over Multiple Chains of Thought

Reference 43

Resolution: verified exact; arxiv_id, observed 2026-05-22T16:06:45.883756Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e4a03570-0332-4bb7-b95e-65484bc90b04 · outbound

This paper cites Generate rather than Retrieve: Large Language Models are Strong Context Generators.

ZeroSearch: Incentivize the Search Capability of LLMs without Searching Generate rather than Retrieve: Large Language Models are Strong Context Generators

Reference 44

Resolution: verified exact; arxiv_id, observed 2026-05-22T16:06:46.013992Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 536128ef-2c81-465e-bf0a-356fbd207ff3 · outbound

This paper cites Zhang, Z.

ZeroSearch: Incentivize the Search Capability of LLMs without Searching Zhang, Z

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T16:06:46.525795Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 802f165d-b378-4788-a62f-47876286c3c1 · outbound

This paper cites A Survey of Large Language Models.

ZeroSearch: Incentivize the Search Capability of LLMs without Searching A Survey of Large Language Models

Reference 46

Resolution: verified exact; local_arxiv, observed 2026-05-22T16:06:45.971752Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ad3c94f8-a89d-43c3-b91c-98cd25a3ee7b · outbound

This paper cites Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions.

ZeroSearch: Incentivize the Search Capability of LLMs without Searching Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions

Reference 47

Resolution: verified exact; arxiv_id, observed 2026-05-22T16:06:46.019822Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 423d9367-d1ce-40c2-bd0c-21b5335575bf · outbound

This paper cites DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments.

ZeroSearch: Incentivize the Search Capability of LLMs without Searching DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments

Reference 48

Resolution: verified exact; local_arxiv, observed 2026-05-22T16:06:45.996945Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d6438004-c379-44e4-9fb9-64d3d0642d2a · outbound

This paper cites an unresolved cited work.

ZeroSearch: Incentivize the Search Capability of LLMs without Searching Unresolved cited work

Reference 49

Resolution: unresolved; raw_fallback, observed 2026-05-22T16:06:46.529694Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Pith citing papers

Observation 766e418f-a43a-43e2-a5ab-47b01d31dc54 · inbound

Group-in-Group Policy Optimization for LLM Agent Training cites this paper.

Group-in-Group Policy Optimization for LLM Agent Training ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 59

Resolution: verified exact; arxiv_id, observed 2026-05-17T17:44:13.577137Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b9b41e95-0d47-481f-b6e2-c4ee79f0e13e · inbound

Visual Agentic Reinforcement Fine-Tuning cites this paper.

Visual Agentic Reinforcement Fine-Tuning ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T15:42:30.760995Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79501cbb-1579-41cb-a840-1559fde82470 · inbound

Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning cites this paper.

Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 71

Resolution: verified exact; local_arxiv, observed 2026-05-22T13:34:53.194692Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation de0a2467-344b-4148-9fc7-a3d9826f11f3 · inbound

AI Scientists Fail Without Strong Implementation Capability cites this paper.

AI Scientists Fail Without Strong Implementation Capability ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T11:49:06.037989Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93347886-c143-41e3-9983-72c4266c1ae7 · inbound

Coordinating Search-Informed Reasoning and Reasoning-Guided Search in Claim Verification cites this paper.

Coordinating Search-Informed Reasoning and Reasoning-Guided Search in Claim Verification ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T05:37:29.355209Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6895831-5c05-4759-82e2-952c8ab45ca1 · inbound

Reinforcement Fine-Tuning for Reasoning towards Multi-Step Multi-Source Search in Large Language Models cites this paper.

Reinforcement Fine-Tuning for Reasoning towards Multi-Step Multi-Source Search in Large Language Models ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T05:20:04.635328Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10349242-37f1-4f2e-b007-f0b20d7ab42a · inbound

L0: Reinforcement Learning to Become General Agents cites this paper.

L0: Reinforcement Learning to Become General Agents ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T21:45:00.471283Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36f5341b-84e6-4057-8771-d0dde25fb063 · inbound

Frustratingly Simple Retrieval Improves Challenging, Reasoning-Intensive Benchmarks cites this paper.

Frustratingly Simple Retrieval Improves Challenging, Reasoning-Intensive Benchmarks ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T21:02:58.300557Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 008a62c4-0b08-4baa-b7a6-220929a6c4dd · inbound

Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs cites this paper.

Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-06T18:00:48.124033Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22083f09-1e21-4c2f-a8e5-958bceee3a81 · inbound

Kimi K2: Open Agentic Intelligence cites this paper.

Kimi K2: Open Agentic Intelligence ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 70

Resolution: verified exact; arxiv_id, observed 2026-05-17T17:44:13.577137Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 64186f76-6f6c-4130-a97c-02440d495a05 · inbound

ParallelSearch: Train your LLMs to Decompose Query and Search Sub-queries in Parallel with Reinforcement Learning cites this paper.

ParallelSearch: Train your LLMs to Decompose Query and Search Sub-queries in Parallel with Reinforcement Learning ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-05T21:12:11.902466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8f7c3d2-1a78-4583-892c-4749ddd15efa · inbound

SSRL: Self-Search Reinforcement Learning cites this paper.

SSRL: Self-Search Reinforcement Learning ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-05T20:17:12.061269Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f716f628-5cd9-4297-9902-194db5bb024b · inbound

Atom-Searcher: Enhancing Agentic Deep Research via Fine-Grained Atomic Thought Reward cites this paper.

Atom-Searcher: Enhancing Agentic Deep Research via Fine-Grained Atomic Thought Reward ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-05T19:21:52.228538Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d5138e2-3aec-4a06-852f-36d9df1b15c8 · inbound

Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL cites this paper.

Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-05T23:57:34.744588Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4aa972d9-522e-40aa-9b7d-71a8afa19c0e · inbound

MUA-RL: Multi-turn User-interacting Agent Reinforcement Learning for agentic tool use cites this paper.

MUA-RL: Multi-turn User-interacting Agent Reinforcement Learning for agentic tool use ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-05T16:22:51.580729Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23b0208c-f8d2-48f6-aa1c-a6b1e0843da2 · inbound

Open Data Synthesis For Deep Research cites this paper.

Open Data Synthesis For Deep Research ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-05T13:45:12.880393Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f2e6797-8687-4eb7-bee6-204b9943b5a4 · inbound

The Landscape of Agentic Reinforcement Learning for LLMs: A Survey cites this paper.

The Landscape of Agentic Reinforcement Learning for LLMs: A Survey ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 291

Resolution: verified exact; local_arxiv, observed 2026-05-18T19:21:48.083190Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation db41b4e9-bbba-4344-965c-9308351cd6bb · inbound

SafeSearch: Automated Red-Teaming of LLM-Based Search Agents cites this paper.

SafeSearch: Automated Red-Teaming of LLM-Based Search Agents ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:53.144738Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe3ef81d-2135-4304-b812-a8ab20d4c57c · inbound

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs cites this paper.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 36

Resolution: verified exact; local_arxiv, observed 2026-05-18T11:11:18.243027Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d6204829-2ac6-47d5-9156-08232c55bac6 · inbound

Beyond Correctness: Rewarding Faithful Reasoning in Retrieval-Augmented Generation cites this paper.

Beyond Correctness: Rewarding Faithful Reasoning in Retrieval-Augmented Generation ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-04T09:50:49.763839Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12b11eef-be01-4a5e-b4f1-bbca7197e53a · inbound

MemSearcher: Training LLMs to Reason, Search and Manage Memory via End-to-End Reinforcement Learning cites this paper.

MemSearcher: Training LLMs to Reason, Search and Manage Memory via End-to-End Reinforcement Learning ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-05-18T01:00:34.427606Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 16849526-b346-475d-b034-e8691d606a4e · inbound

TeaRAG: A Token-Efficient Agentic Retrieval-Augmented Generation Framework cites this paper.

TeaRAG: A Token-Efficient Agentic Retrieval-Augmented Generation Framework ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-03T23:33:48.943481Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73b02692-f7b7-4c8a-975d-e4e06361df7f · inbound

Agentic Reasoning for Large Language Models cites this paper.

Agentic Reasoning for Large Language Models ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 240

Resolution: verified exact; arxiv_id, observed 2026-05-17T17:44:13.577137Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3be6609d-e3ea-4139-b1a0-b2be409ba534 · inbound

CLEANER: Self-Purified Trajectories Boost Agentic Reinforcement Learning cites this paper.

CLEANER: Self-Purified Trajectories Boost Agentic Reinforcement Learning ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-03T09:01:50.680369Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b57a5ae9-9675-44ca-b679-12f0db223c91 · inbound

$\pi$-Play: Multi-Agent Self-Play via Privileged Self-Distillation without External Data cites this paper.

$\pi$-Play: Multi-Agent Self-Play via Privileged Self-Distillation without External Data ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-05-17T17:44:13.577137Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5bcc6c5a-e832-4678-a87d-b6ae444c3fe8 · inbound

Democratizing Tool Learning with Environments Fully Simulated by a Free 8B Language Model cites this paper.

Democratizing Tool Learning with Environments Fully Simulated by a Free 8B Language Model ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 36

Resolution: verified exact; arxiv_id, observed 2026-05-17T17:44:13.577137Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7439fd0e-d087-48cd-910f-f2b9a7c28086 · inbound

LiteResearcher: A Scalable Agentic RL Training Framework for Deep Research Agent cites this paper.

LiteResearcher: A Scalable Agentic RL Training Framework for Deep Research Agent ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 30

Resolution: verified exact; local_arxiv, observed 2026-07-05T15:11:10.910914Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 51c56807-6fdc-4e42-85e4-c32c286a1916 · inbound

Negative Advantages Is a Double-Edged Sword: Calibrating advantages in GRPO for Search Agents cites this paper.

Negative Advantages Is a Double-Edged Sword: Calibrating advantages in GRPO for Search Agents ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-17T17:44:13.577137Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 29d844e5-b155-48d3-84be-153d48aafdb8 · inbound

T$^2$PO: Uncertainty-Guided Exploration Control for Stable Multi-Turn Agentic Reinforcement Learning cites this paper.

T$^2$PO: Uncertainty-Guided Exploration Control for Stable Multi-Turn Agentic Reinforcement Learning ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-17T17:44:13.577137Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b485c50b-9bf8-4e07-bb59-75be265f5cbf · inbound

LatentRAG: Latent Reasoning and Retrieval for Efficient Agentic RAG cites this paper.

LatentRAG: Latent Reasoning and Retrieval for Efficient Agentic RAG ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 78

Resolution: verified exact; arxiv_id, observed 2026-05-17T17:44:13.577137Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation bc9d25c7-4730-461e-8e89-f2e2fc2b278d · inbound

Learning CLI Agents with Structured Action Credit under Selective Observation cites this paper.

Learning CLI Agents with Structured Action Credit under Selective Observation ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 49

Resolution: verified exact; arxiv_id, observed 2026-05-17T17:44:13.577137Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e43be5d5-2fe0-4908-97a7-d618bf063802 · inbound

AIPO: Learning to Reason from Active Interaction cites this paper.

AIPO: Learning to Reason from Active Interaction ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 61

Resolution: verified exact; arxiv_id, observed 2026-05-17T17:44:13.577137Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 559bdfe8-c823-4392-ba6b-9cbcbc4324e2 · inbound

AIPO: Learning to Reason from Active Interaction cites this paper.

AIPO: Learning to Reason from Active Interaction ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 61

Resolution: verified exact; local_arxiv, observed 2026-05-19T18:07:42.331737Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation bf02f1e9-a3dc-4062-ab52-6d3b0dd54dc8 · inbound

SearchSkill: Teaching LLMs to Use Search Tools with Evolving Skill Banks cites this paper.

SearchSkill: Teaching LLMs to Use Search Tools with Evolving Skill Banks ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-05-17T17:44:13.577137Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d5de3ec6-3243-47ec-b011-7eadbf60298c · inbound

SearchSkill: Teaching LLMs to Use Search Tools with Evolving Skill Banks cites this paper.

SearchSkill: Teaching LLMs to Use Search Tools with Evolving Skill Banks ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-05-17T17:44:13.577137Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d83ba957-1563-4da2-9816-76e7ac6c15b3 · inbound

SearchSkill: Teaching LLMs to Use Search Tools with Evolving Skill Banks cites this paper.

SearchSkill: Teaching LLMs to Use Search Tools with Evolving Skill Banks ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-07-01T13:35:46.393276Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 199c9419-5388-4586-ae47-1dfce34e6936 · inbound

PiCA: Pivot-Based Credit Assignment for Search Agentic Reinforcement Learning cites this paper.

PiCA: Pivot-Based Credit Assignment for Search Agentic Reinforcement Learning ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-17T17:44:13.577137Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation cdd216db-0d6b-4217-85ab-86b397374766 · inbound

PiCA: Pivot-Based Credit Assignment for Search Agentic Reinforcement Learning cites this paper.

PiCA: Pivot-Based Credit Assignment for Search Agentic Reinforcement Learning ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-17T17:44:13.577137Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 4096f320-eb29-4b79-ba67-c64511a8a520 · inbound

CuSearch: Curriculum Rollout Sampling via Search Depth for Agentic RAG cites this paper.

CuSearch: Curriculum Rollout Sampling via Search Depth for Agentic RAG ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-17T17:44:13.577137Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b710c942-97ec-45a3-af78-98468e34fed5 · inbound

CuSearch: Curriculum Rollout Sampling via Search Depth for Agentic RAG cites this paper.

CuSearch: Curriculum Rollout Sampling via Search Depth for Agentic RAG ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-17T17:44:13.577137Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 37ee4269-071f-40d9-8e63-60562d2d8a6f · inbound

SkillGraph: Skill-Augmented Reinforcement Learning for Agents via Evolving Skill Graphs cites this paper.

SkillGraph: Skill-Augmented Reinforcement Learning for Agents via Evolving Skill Graphs ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 12

Resolution: metadata mismatch; arxiv_id, observed 2026-05-17T17:44:13.577137Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0fe2ae17-37ae-4eb8-bc64-1fa77e860d0c · inbound

Retrieval is Cheap, Show Me the Code: Executable Multi-Hop Reasoning for Retrieval-Augmented Generation cites this paper.

Retrieval is Cheap, Show Me the Code: Executable Multi-Hop Reasoning for Retrieval-Augmented Generation ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 37

Resolution: verified exact; arxiv_id, observed 2026-05-17T17:44:13.577137Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6f814467-b9ee-4b49-b10a-c2e48f6ce90f · inbound

Scaling Retrieval-Augmented Reasoning with Parallel Search and Explicit Merging cites this paper.

Scaling Retrieval-Augmented Reasoning with Parallel Search and Explicit Merging ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-17T17:44:13.577137Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation bd76b198-0484-4797-a215-4a5064b3844a · inbound

Harnessing LLM Agents with Skill Programs cites this paper.

Harnessing LLM Agents with Skill Programs ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-05-20T11:28:14.390559Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7db8312f-42c3-4704-a05b-20e072a41525 · inbound

Search-E1: Self-Distillation Drives Self-Evolution in Search-Augmented Reasoning cites this paper.

Search-E1: Self-Distillation Drives Self-Evolution in Search-Augmented Reasoning ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-05-22T06:11:09.200380Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ef40330c-fca1-40a6-80d9-1858a719b5bc · inbound

Search-E1: Self-Distillation Drives Self-Evolution in Search-Augmented Reasoning cites this paper.

Search-E1: Self-Distillation Drives Self-Evolution in Search-Augmented Reasoning ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-06-30T17:24:56.781911Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2a43c6e3-957f-420f-b0e5-e55efa8a6488 · inbound

When Denser Credit Is Not Enough: Evidence-Calibrated Policy Optimization for Long-Horizon LLM Agent Training cites this paper.

When Denser Credit Is Not Enough: Evidence-Calibrated Policy Optimization for Long-Horizon LLM Agent Training ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 47

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T12:16:56.822885Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 9dc86ad0-4ac1-4ba5-9ff1-3600745d6288 · inbound

Co-Evolving Skill Generation and Policy Optimization cites this paper.

Co-Evolving Skill Generation and Policy Optimization ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 93

Resolution: verified exact; local_arxiv, observed 2026-07-02T22:57:25.864373Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7ae2de35-6a05-4370-bc23-5c95b372bfb7 · inbound

Toward Generalist Autonomous Research via Hypothesis-Tree Refinement cites this paper.

Toward Generalist Autonomous Research via Hypothesis-Tree Refinement ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 46

Resolution: verified exact; local_arxiv, observed 2026-06-27T09:40:47.097442Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b7e44d8e-843d-462d-ad2b-af0233ab18c2 · inbound

Qwen-AgentWorld: Language World Models for General Agents cites this paper.

Qwen-AgentWorld: Language World Models for General Agents ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 50

Resolution: verified exact; local_arxiv, observed 2026-07-04T17:09:59.265833Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 4cab1aee-f6e4-48a5-b6e5-093351b2ae91 · inbound

DocArena: Turning Raw Documents into Controllable Training Environments for Document Search Agents cites this paper.

DocArena: Turning Raw Documents into Controllable Training Environments for Document Search Agents ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 44

Resolution: metadata mismatch; local_arxiv, observed 2026-06-29T12:53:26.563622Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 103ef9eb-cb44-456a-ad4d-66b729fe8c23 · inbound

R$^2$-Searcher: Calibrating Retrieval and Reasoning Boundaries for Agentic Search cites this paper.

R$^2$-Searcher: Calibrating Retrieval and Reasoning Boundaries for Agentic Search ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 36

Resolution: verified exact; local_arxiv, observed 2026-06-30T00:34:05.139160Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b32128c3-ab09-4cec-a14d-6bb8bec4572d · inbound

To Reason or to Fabricate: Reasoning Without Shortcuts via Hint-Anchored Pairwise Aggregation cites this paper.

To Reason or to Fabricate: Reasoning Without Shortcuts via Hint-Anchored Pairwise Aggregation ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 5

Resolution: metadata mismatch; local_arxiv, observed 2026-06-30T07:44:21.403934Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 08704826-403a-4b63-952a-051391a0acb1 · inbound

As We May Search cites this paper.

As We May Search ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 52

Resolution: verified exact; local_arxiv, observed 2026-06-30T07:34:21.901873Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b6e6b803-b3e4-4c18-b02e-95996769c389 · inbound

CheckRLM: Effective Knowledge-Thought Coherence Checking in Retrieval-Augmented Reasoning cites this paper.

CheckRLM: Effective Knowledge-Thought Coherence Checking in Retrieval-Augmented Reasoning ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 2

Resolution: metadata mismatch; local_arxiv, observed 2026-07-03T14:28:31.086964Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5c063ef8-7448-4456-9872-05c7a28ec0d3 · inbound

Agent Reinforcement Learning via Pivotal-Aware Self-Feedback Retry cites this paper.

Agent Reinforcement Learning via Pivotal-Aware Self-Feedback Retry ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-12T00:33:06.488657Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76a4e2d2-bb8f-4746-9e5b-1a996670f524 · inbound

Information Gain-based Rollout Policy Optimization: An Adaptive Tree-Structured Rollout Approach for Multi-Turn LLM Agents cites this paper.

Information Gain-based Rollout Policy Optimization: An Adaptive Tree-Structured Rollout Approach for Multi-Turn LLM Agents ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-07-08T13:04:56.726732Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 61c6a9c4-2f4c-43d9-9be1-39d977a9439b · inbound

STEC: Evidence Compression for Deep Search in Open-domain Multi-Hop QA cites this paper.

STEC: Evidence Compression for Deep Search in Open-domain Multi-Hop QA ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-14T09:13:24.763990Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a5977e5-3777-483c-80ee-a4e0d6a19add · inbound

DeepStress: Stress-Testing Deep Search Agents cites this paper.

DeepStress: Stress-Testing Deep Search Agents ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-02T03:23:38.114661Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9aa12024-a25e-4e43-98da-c46e8c6782fd · inbound

TRACE: Turn-level Reward Assignment via Credit Estimation for Long-Horizon Agents cites this paper.

TRACE: Turn-level Reward Assignment via Credit Estimation for Long-Horizon Agents ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-02T03:10:51.595241Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd6c5b9b-c9c2-421b-962b-f0f5f56503ae · inbound

From Outcomes to Actions: Leveraging Hindsight for Long-Horizon Language Agent Training cites this paper.

From Outcomes to Actions: Leveraging Hindsight for Long-Horizon Language Agent Training ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T09:45:49.601208Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c1bf993-9c97-46b7-a545-892b5d0e4681 · inbound

PROGRESS: Coverage-guided RL to Train Search-augmented LLM Agent cites this paper.

PROGRESS: Coverage-guided RL to Train Search-augmented LLM Agent ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T00:37:24.709002Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fac8333a-c316-4e68-9ba0-c7d119a48a70 · inbound

BiCAA: Bidirectional Credit Assignment for Search-Augmented Agent cites this paper.

BiCAA: Bidirectional Credit Assignment for Search-Augmented Agent ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T00:23:00.140200Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c00a61b-45e2-4fd6-9c17-16930eff3e74 · inbound

Fetch-then-Explore: Decoupling Selection from Extraction over a Persistent Workspace for Search Agents cites this paper.

Fetch-then-Explore: Decoupling Selection from Extraction over a Persistent Workspace for Search Agents ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 133

Resolution: unresolved; no resolver link, observed 2026-08-04T15:12:55.859971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.