Paper Citation Record · LEDGER

ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment

As of 15 August 2026, this Paper Citation Record lists 26 of 26 outbound references and 0 inbound Pith citation observations for arXiv:2608.05102.

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

pith.paper-citation-record.v1
2608.05102 v1

Coverage vector

measured 26 of 26 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T05:19:21.185995Z

measured 26 of 26 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-14T06:32:32.682623+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

26 of 26 outbound references displayed

verified exact2
verified fuzzy3
unresolved21
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 079c162c-d591-4b99-9867-07ee0597621c · outbound

This paper cites Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity.

ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T05:19:19.445970Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58537edf-35b3-4544-b9a4-36ce491ad94d · outbound

This paper cites xbench: Tracking Agents Productivity Scaling with Profession-Aligned Real-World Evaluations.

ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment xbench: Tracking Agents Productivity Scaling with Profession-Aligned Real-World Evaluations

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T05:19:19.613381Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 534cf684-4a1e-40ff-9a7c-1e03f1c873ff · outbound

This paper cites Openseeker: Democ- ratizing frontier search agents by fully open-sourcing training data.arXiv preprint arXiv:2603.15594,.

ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment Openseeker: Democ- ratizing frontier search agents by fully open-sourcing training data.arXiv preprint arXiv:2603.15594,

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T05:19:19.643329Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1eb7d9d7-02b4-4ba1-b101-dc17139bcdef · outbound

This paper cites Beyond ten turns: Unlocking long-horizon agentic search with large-scale asynchronous rl.arXiv preprint arXiv:2508.07976,.

ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment Beyond ten turns: Unlocking long-horizon agentic search with large-scale asynchronous rl.arXiv preprint arXiv:2508.07976,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T05:19:19.725925Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6073a32a-6fd7-440d-8092-e06265ccce10 · outbound

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

ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T05:19:19.789944Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85ceb175-2074-47f2-9e7c-9c87469400cb · outbound

This paper cites Beyond Trajectory Rewards: Step-level Credit Assignment for Agentic Search via Graph Modeling.

ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment Beyond Trajectory Rewards: Step-level Credit Assignment for Agentic Search via Graph Modeling

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-08-06T05:19:21.725226Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7182ef0a-fcd6-4acd-b1be-9eba0d03e0e4 · outbound

This paper cites LongSeeker: Elastic Context Orchestration for Long-Horizon Search Agents.

ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment LongSeeker: Elastic Context Orchestration for Long-Horizon Search Agents

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T05:19:20.017984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8bb2c174-3c94-4225-96bc-91a934928ac8 · outbound

This paper cites Gaia: a benchmark for general ai assistants.

ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment Gaia: a benchmark for general ai assistants

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T05:19:20.095118Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78975520-a5e0-42ad-8ff5-cf32e7075f9e · outbound

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

ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T05:19:20.161920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba93d120-09b2-4872-a389-c08fa53e3187 · outbound

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

ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T05:19:20.306285Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c038844-3826-4427-866d-6440e3972f09 · outbound

This paper cites Beyond turn limits: Training deep search agents with dynamic context window.

ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment Beyond turn limits: Training deep search agents with dynamic context window

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T05:19:20.401077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e50ffa6-bafb-4501-b608-b30ac602a4db · outbound

This paper cites Mind DeepResearch Technical Report.

ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment Mind DeepResearch Technical Report

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T05:19:20.448590Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30dd4e21-755c-477f-9dc3-b1a38bd77bf3 · outbound

This paper cites Mirothinker-1.7 & h1: Towards heavy-duty research agents via verification.arXiv preprint arXiv:2603.15726, 2026a.

ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment Mirothinker-1.7 & h1: Towards heavy-duty research agents via verification.arXiv preprint arXiv:2603.15726, 2026a

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T05:19:20.515706Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1276f3eb-a740-458f-a3f9-73bf57d05b5c · outbound

This paper cites DR-Venus: Towards Frontier Edge-Scale Deep Research Agents with Only 10K Open Data.

ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment DR-Venus: Towards Frontier Edge-Scale Deep Research Agents with Only 10K Open Data

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T05:19:20.556350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82411ddd-a6e5-4f9e-ad9b-c7be4dfe83f8 · outbound

This paper cites BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents.

ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T05:19:20.621113Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1dbad30-8a63-4ca4-8177-d2817fd13b68 · outbound

This paper cites QUEST: Training Frontier Deep Research Agents with Fully Synthetic Tasks.

ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment QUEST: Training Frontier Deep Research Agents with Fully Synthetic Tasks

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-08-06T05:19:21.342613Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e386d428-a3ce-47a5-b67a-d566234a29c3 · outbound

This paper cites Deepseek-v4: Towards highly efficient million-token context intelligence.arXiv preprint arXiv:2606.19348,.

ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment Deepseek-v4: Towards highly efficient million-token context intelligence.arXiv preprint arXiv:2606.19348,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T05:19:20.769198Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38ab4a2f-af27-4d1f-97ed-df315739fc0d · outbound

This paper cites Qwen3 Technical Report.

ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment Qwen3 Technical Report

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T05:19:20.822156Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd32152d-f00c-4197-873e-667b8ddad1b4 · outbound

This paper cites React: Synergizing reasoning and acting in language models.

ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment React: Synergizing reasoning and acting in language models

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:19:22.414685Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 0fd0eee8-aa52-4aeb-9fcd-67fc7716aa08 · outbound

This paper cites Deepresearcher: Scaling deep research via reinforcement learning in real-world environments.

ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment Deepresearcher: Scaling deep research via reinforcement learning in real-world environments

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:19:22.266158Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 2d48fb0c-fc8a-401e-af39-fc47e3540e10 · outbound

This paper cites BrowseComp-ZH: Benchmarking Web Browsing Ability of Large Language Models in Chinese.

ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment BrowseComp-ZH: Benchmarking Web Browsing Ability of Large Language Models in Chinese

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T05:19:21.114990Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 954ad8f9-1de2-4d67-a164-bd308d2ceb60 · outbound

This paper cites We randomly select 8.5K trajectories from OpenSeeker (Du et al., 2026), consisting of 5.5K correct and 3.0K incorrect trajectories.

ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment We randomly select 8.5K trajectories from OpenSeeker (Du et al., 2026), consisting of 5.5K correct and 3.0K incorrect trajectories

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:19:22.080853Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e2a95e4a-0c76-40f8-9aa3-9396262f89d8 · outbound

This paper cites GLM-5: from Vibe Coding to Agentic Engineering.

ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment GLM-5: from Vibe Coding to Agentic Engineering

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-06T05:19:20.957874Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f681e7c2-36df-48a3-a46b-6ae12c0e3b1b · outbound

This paper cites OpenAI GPT-5 System Card.

ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment OpenAI GPT-5 System Card

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-06T05:19:20.252727Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba17dd90-815e-4f20-992c-a437c932fcaa · outbound

This paper cites Verified Critical Step Optimization for LLM Agents.

ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment Verified Critical Step Optimization for LLM Agents

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-06T05:19:19.864892Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31aa451b-fd91-46e1-9610-f479790c1007 · outbound

This paper cites Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity.

ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity

Reference 2026

Resolution: unresolved; no resolver link, observed 2026-08-06T05:19:19.519704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.