Scaling Automatic Research Agents via World Models | Paper Citation Record

Observation 7c2d0b47-dbc7-4ba4-b8e2-e18216e49ae4 · outbound

This paper cites The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery.

Scaling Automatic Research Agents via World Models The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-16T00:11:05.283953Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec215b5f-35c3-4aab-91ec-11f18071cb5e · outbound

This paper cites Towards an AI co-scientist.

Scaling Automatic Research Agents via World Models Towards an AI co-scientist

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-16T00:11:05.290228Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e739cc44-fa7d-4bc4-9bea-3306fe2b801d · outbound

This paper cites Agent Laboratory: Using LLM Agents as Research Assistants.

Scaling Automatic Research Agents via World Models Agent Laboratory: Using LLM Agents as Research Assistants

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-16T00:11:05.295789Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5264f757-8978-433b-a3d4-cccf44dd7a7f · outbound

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

Scaling Automatic Research Agents via World Models ReAct: Synergizing reasoning and acting in language models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-16T00:11:05.301305Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6851048e-6496-4525-a9f5-200d3a5d36a3 · outbound

This paper cites Tree of thoughts: Deliberate problem solving with large language models.

Scaling Automatic Research Agents via World Models Tree of thoughts: Deliberate problem solving with large language models

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:11:06.815673Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 2be3fba0-ce69-4de5-b1b8-a0b462ea6457 · outbound

This paper cites Reflexion: Language agents with verbal reinforcement learning.

Scaling Automatic Research Agents via World Models Reflexion: Language agents with verbal reinforcement learning

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:11:06.800489Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 2f9c642f-3d07-4108-95be-3c82526bd47e · outbound

This paper cites Boiko, Robert MacKnight, Ben Kline, and Gabe Gomes.

Scaling Automatic Research Agents via World Models Boiko, Robert MacKnight, Ben Kline, and Gabe Gomes

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-16T00:11:05.317141Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cfb74660-e33f-4f0c-b01c-e6db6ae5b493 · outbound

This paper cites Augmenting large language models with chemistry tools.Nature Machine Intelligence, 6(5):525–535, 2024.

Scaling Automatic Research Agents via World Models Augmenting large language models with chemistry tools.Nature Machine Intelligence, 6(5):525–535, 2024

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:11:06.773718Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 36d5b75f-7e46-420b-8033-370916790f13 · outbound

This paper cites An autonomous laboratory for the accelerated synthesis of novel inorganic materials.Nature, 624:86–91, 2023.

Scaling Automatic Research Agents via World Models An autonomous laboratory for the accelerated synthesis of novel inorganic materials.Nature, 624:86–91, 2023

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:11:06.757818Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 4d2c54d5-b03b-47c7-8283-72f98edf4951 · outbound

This paper cites AIDE: AI-Driven Exploration in the Space of Code.

Scaling Automatic Research Agents via World Models AIDE: AI-Driven Exploration in the Space of Code

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-16T00:11:05.330947Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c92a7e88-e0d7-4683-b7a3-8df5f8fc1483 · outbound

This paper cites DS-Agent: Automated data science by empowering large language models with case-based reasoning.

Scaling Automatic Research Agents via World Models DS-Agent: Automated data science by empowering large language models with case-based reasoning

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:11:06.743544Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation b8a2f26d-6207-4fed-8109-db7b81ec4956 · outbound

This paper cites MLAgentBench: Evaluating language agents on machine learning experimentation.

Scaling Automatic Research Agents via World Models MLAgentBench: Evaluating language agents on machine learning experimentation

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:11:06.728662Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 5a8b0a89-9c0e-453a-8806-78185b3a7665 · outbound

This paper cites Proximal Policy Optimization Algorithms.

Scaling Automatic Research Agents via World Models Proximal Policy Optimization Algorithms

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-16T00:11:05.345933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation efb3001a-af35-4f44-b3d8-005113899b11 · outbound

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

Scaling Automatic Research Agents via World Models DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-16T00:11:05.350677Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 097dac6f-4047-4b2d-b1dc-10f19f94605b · outbound

This paper cites Tulu 3: Pushing Frontiers in Open Language Model Post-Training.

Scaling Automatic Research Agents via World Models Tulu 3: Pushing Frontiers in Open Language Model Post-Training

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-16T00:11:05.355314Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 998db60e-2b3d-4e9e-8844-e11e53591ed9 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

Scaling Automatic Research Agents via World Models DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-16T00:11:05.360160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a81ed9b4-8c04-4747-b143-f9f3a31a40d7 · outbound

This paper cites Gonzalez, Hao Zhang, and Ion Stoica.

Scaling Automatic Research Agents via World Models Gonzalez, Hao Zhang, and Ion Stoica

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:11:06.714482Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 6c51220d-6fe0-404e-b0f9-e5c60f8ca9dc · outbound

This paper cites Gonzalez, Clark Barrett, and Ying Sheng.

Scaling Automatic Research Agents via World Models Gonzalez, Clark Barrett, and Ying Sheng

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-16T00:11:05.368716Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25e21d07-2a55-48e6-993c-df7cce75a138 · outbound

This paper cites MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning Engineering.

Scaling Automatic Research Agents via World Models MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning Engineering

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-16T00:11:05.373386Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 608f95c0-b593-4d83-ae20-28bf0dc520cc · outbound

This paper cites SWE-World: Building software engineering agents in docker-free environments.arXiv preprint arXiv:2602.03419, 2026.

Scaling Automatic Research Agents via World Models SWE-World: Building software engineering agents in docker-free environments.arXiv preprint arXiv:2602.03419, 2026

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-16T00:11:05.378163Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2655ffa2-dfcb-4c73-bb60-31ff3095b7d9 · outbound

This paper cites World Models.

Scaling Automatic Research Agents via World Models World Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-16T00:11:05.382737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa1922a4-b213-41d8-903f-f5d416327c43 · outbound

This paper cites Mastering diverse control tasks through world models.Nature, 640(8059):647–653, 2025.

Scaling Automatic Research Agents via World Models Mastering diverse control tasks through world models.Nature, 640(8059):647–653, 2025

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-16T00:11:05.387851Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fcdf4f54-da5b-4440-a27c-ca89974482f3 · outbound

This paper cites AlphaEvolve: A coding agent for scientific and algorithmic discovery.

Scaling Automatic Research Agents via World Models AlphaEvolve: A coding agent for scientific and algorithmic discovery

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-16T00:11:05.392258Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 727bb985-c958-41d2-bc63-37c8b6f31c0c · outbound

This paper cites The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search.

Scaling Automatic Research Agents via World Models The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-16T00:11:05.396676Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b93fff4c-4f57-4476-85b5-bf4b9100212c · outbound

This paper cites Autodata: An agentic data scientist to create high quality synthetic data.

Scaling Automatic Research Agents via World Models Autodata: An agentic data scientist to create high quality synthetic data

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-08-16T00:11:06.016028Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 61e3b663-eceb-4065-be7b-e0846ee531c6 · outbound

This paper cites Many ai analysts, one dataset: Navigating the agentic data science multiverse.Proceedings of the National Academy of Sciences, 123(29):e2606495123, 2026.

Scaling Automatic Research Agents via World Models Many ai analysts, one dataset: Navigating the agentic data science multiverse.Proceedings of the National Academy of Sciences, 123(29):e2606495123, 2026

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:11:06.679606Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation e294bd39-cd7a-4ec8-b399-db27afb1a928 · outbound

This paper cites Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering.

Scaling Automatic Research Agents via World Models Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-08-16T00:11:05.992329Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 4f3c2a86-73fa-4561-927b-0f3d5231c03a · outbound

This paper cites First steps toward automated AI research.https://www.recursive.com/articles/ first-steps-toward-automated-ai-research, 2026.

Scaling Automatic Research Agents via World Models First steps toward automated AI research.https://www.recursive.com/articles/ first-steps-toward-automated-ai-research, 2026

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:11:06.662919Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation a45f5d05-2779-4526-9a76-dded855d8324 · outbound

This paper cites MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering.

Scaling Automatic Research Agents via World Models MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-16T00:11:05.421563Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0505398e-866a-4ed1-b3b9-e530c2833f49 · outbound

This paper cites DSBench: How Far Are Data Science Agents from Becoming Data Science Experts?.

Scaling Automatic Research Agents via World Models DSBench: How Far Are Data Science Agents from Becoming Data Science Experts?

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-16T00:11:05.426462Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6eaa9709-9a1e-41b6-bf51-9d6997341e93 · outbound

This paper cites MLGym: A New Framework and Benchmark for Advancing AI Research Agents.

Scaling Automatic Research Agents via World Models MLGym: A New Framework and Benchmark for Advancing AI Research Agents

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-16T00:11:05.431277Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af1390d8-b1e8-4ff5-9714-483ba9b94d05 · outbound

This paper cites SWE-bench: Can language models resolve real-world GitHub issues? InInternational Conference on Learning Representations, 2024.

Scaling Automatic Research Agents via World Models SWE-bench: Can language models resolve real-world GitHub issues? InInternational Conference on Learning Representations, 2024

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:11:06.648357Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation b3e4f2f7-3fe1-4c38-a482-0b6eb81bba12 · outbound

This paper cites SWE-agent: Agent-computer interfaces enable automated software engineering.

Scaling Automatic Research Agents via World Models SWE-agent: Agent-computer interfaces enable automated software engineering

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:11:06.633550Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 7dc99044-2aa0-45e3-b06e-b3a9fb5adf76 · outbound

This paper cites OpenHands: An open platform for AI software developers as generalist agents.

Scaling Automatic Research Agents via World Models OpenHands: An open platform for AI software developers as generalist agents

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:11:06.619381Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation c4568b76-f7fa-40a3-b4df-164256650064 · outbound

This paper cites Training software engineering agents and verifiers with SWE-Gym.

Scaling Automatic Research Agents via World Models Training software engineering agents and verifiers with SWE-Gym

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:11:06.604504Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 77e6e16d-97a1-4c87-82ff-1700845d1341 · outbound

This paper cites HybridFlow: A Flexible and Efficient RLHF Framework.

Scaling Automatic Research Agents via World Models HybridFlow: A Flexible and Efficient RLHF Framework

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-16T00:11:05.454659Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42822062-6128-46d8-a4c2-8edd867ce859 · outbound

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

Scaling Automatic Research Agents via World Models QUEST: Training Frontier Deep Research Agents with Fully Synthetic Tasks

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-16T00:11:05.459539Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a07e5786-d97b-4376-98c6-c8452eca5218 · outbound

This paper cites DAPO: An Open-Source LLM Reinforcement Learning System at Scale.

Scaling Automatic Research Agents via World Models DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-16T00:11:05.464570Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5cc2bb77-c737-4729-b13d-ecde956b9baa · outbound

This paper cites POPE: Learning to reason on hard problems via privileged on-policy exploration.arXiv preprint arXiv:2601.18779, 2026.

Scaling Automatic Research Agents via World Models POPE: Learning to reason on hard problems via privileged on-policy exploration.arXiv preprint arXiv:2601.18779, 2026

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-16T00:11:05.469995Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d46434a-3322-4aa5-b9c2-da49b6751cd6 · outbound

This paper cites an unresolved cited work.

Scaling Automatic Research Agents via World Models Unresolved cited work

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-16T00:11:05.475411Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 434dd338-9b49-4224-a160-fa6205ecd68f · outbound

This paper cites Xing, Hao Zhang, Joseph E.

Scaling Automatic Research Agents via World Models Xing, Hao Zhang, Joseph E

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:11:06.578742Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation e1b38f00-1767-42d9-868a-59087a1c57fd · outbound

This paper cites Genie: Generative interactive environments.

Scaling Automatic Research Agents via World Models Genie: Generative interactive environments

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-16T00:11:05.484296Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a92242f-485b-4bb6-a579-4539cd83e6c0 · outbound

This paper cites Cosmos World Foundation Model Platform for Physical AI.

Scaling Automatic Research Agents via World Models Cosmos World Foundation Model Platform for Physical AI

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-16T00:11:05.488861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0be95e50-7915-4645-b531-0f2bfda7f7a1 · outbound

This paper cites Generating code world models with large language models guided by monte carlo tree search.

Scaling Automatic Research Agents via World Models Generating code world models with large language models guided by monte carlo tree search

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:11:06.551364Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 48c3c47c-a4e5-45d4-9e33-19e18bde0b75 · outbound

This paper cites Worldcoder, a model-based LLM agent: Building world models by writing code and interacting with the environment.

Scaling Automatic Research Agents via World Models Worldcoder, a model-based LLM agent: Building world models by writing code and interacting with the environment

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:11:06.534218Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 0add552b-e8ed-4733-9d3c-07bc712ab87f · outbound

This paper cites Scaling laws for reward model overoptimization.

Scaling Automatic Research Agents via World Models Scaling laws for reward model overoptimization

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:11:06.517603Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 7cf83f13-c3f8-4400-bff5-fc5fbf52264a · outbound

This paper cites Reward model ensembles help mitigate overoptimization.

Scaling Automatic Research Agents via World Models Reward model ensembles help mitigate overoptimization

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-16T00:11:05.506885Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8d2a9b0-60ed-46c8-801d-1ddebbd4ebb6 · outbound

This paper cites On the Convergence of SGD with Biased Gradients.

Scaling Automatic Research Agents via World Models On the Convergence of SGD with Biased Gradients

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-16T00:11:05.511374Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40081426-dc0a-4591-b720-63c76cae791d · outbound

This paper cites Transforming classifier scores into accurate multiclass probability estimates.

Scaling Automatic Research Agents via World Models Transforming classifier scores into accurate multiclass probability estimates

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:11:06.491718Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation e29755e3-d629-4b54-b256-905a8540f44f · outbound

This paper cites Weinberger.

Scaling Automatic Research Agents via World Models Weinberger

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:11:06.476606Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 22e5339a-5e71-4db2-a980-5bf5b3ec5c50 · outbound

This paper cites DualDICE: Behavior-agnostic estimation of dis- counted stationary distribution corrections.

Scaling Automatic Research Agents via World Models DualDICE: Behavior-agnostic estimation of dis- counted stationary distribution corrections

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:11:06.461678Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation a6382609-e0a2-4fe0-8531-82afb58b13ba · outbound

This paper cites Off-policy reinforcement learning with optimistic exploration and distribution correction.

Scaling Automatic Research Agents via World Models Off-policy reinforcement learning with optimistic exploration and distribution correction

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:11:06.446683Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation a4f085af-e9f9-4413-b738-6e5db8a27260 · outbound

This paper cites ML-Agent: Reinforcing LLM Agents for Autonomous Machine Learning Engineering.

Scaling Automatic Research Agents via World Models ML-Agent: Reinforcing LLM Agents for Autonomous Machine Learning Engineering

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-16T00:11:05.534174Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 931b5f53-4014-4541-96f2-c79484996c52 · outbound

This paper cites AceGRPO: Adaptive Curriculum Enhanced Group Relative Policy Optimization for Autonomous Machine Learning Engineering.

Scaling Automatic Research Agents via World Models AceGRPO: Adaptive Curriculum Enhanced Group Relative Policy Optimization for Autonomous Machine Learning Engineering

Reference 54

Resolution: verified exact; local_arxiv, observed 2026-08-16T00:11:05.694818Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation b4ebe061-87de-4c81-8d1b-b4e06b75495b · outbound

This paper cites Synthetic Sandbox for Training Machine Learning Engineering Agents.

Scaling Automatic Research Agents via World Models Synthetic Sandbox for Training Machine Learning Engineering Agents

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-16T00:11:05.543606Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 258d2b2b-c7bb-4594-aecb-bbef8ebe5e24 · outbound

This paper cites LIBERO: Benchmarking knowledge transfer for lifelong robot learning.

Scaling Automatic Research Agents via World Models LIBERO: Benchmarking knowledge transfer for lifelong robot learning

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-16T00:11:05.548699Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f722c6a-2621-4e57-b941-9299e84a6c90 · outbound

This paper cites Qwen3.5.https://qwen.ai/blog?id=qwen3.5, 2026.

Scaling Automatic Research Agents via World Models Qwen3.5.https://qwen.ai/blog?id=qwen3.5, 2026

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:11:06.421910Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 0acf7aba-d5b9-4189-85f7-437edab02770 · outbound

This paper cites MiniVLA: A better VLA with a smaller footprint.https://github.

Scaling Automatic Research Agents via World Models MiniVLA: A better VLA with a smaller footprint.https://github

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:11:06.407362Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation fbe222f3-aea4-4d1b-be1b-3dc0f9e6f7ac · outbound

This paper cites Robometer: Scaling General-Purpose Robotic Reward Models via Trajectory Comparisons.

Scaling Automatic Research Agents via World Models Robometer: Scaling General-Purpose Robotic Reward Models via Trajectory Comparisons

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-16T00:11:05.562900Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c86dc91e-9618-40e4-a4fa-8381b0ff4eb5 · outbound

This paper cites OpenVLA: An open-source vision-language- action model.

Scaling Automatic Research Agents via World Models OpenVLA: An open-source vision-language- action model

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:11:06.393065Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ea2d7fe4-75e9-4aa2-b88f-26fcb03f74bc · outbound

This paper cites $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization.

Scaling Automatic Research Agents via World Models $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-16T00:11:05.572219Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a0f3628-7a74-40be-b8e6-fa3f01de429c · outbound

This paper cites Latent reasoning VLA: Latent thinking and prediction for vision-language-action models.

Scaling Automatic Research Agents via World Models Latent reasoning VLA: Latent thinking and prediction for vision-language-action models

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:11:06.378180Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation f4bb520c-473f-45fd-ba80-13a0355d188c · outbound

This paper cites Finite-time analysis of the multiarmed bandit problem.Machine Learning, 47:235–256, 2002.

Scaling Automatic Research Agents via World Models Finite-time analysis of the multiarmed bandit problem.Machine Learning, 47:235–256, 2002

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-16T00:11:05.581626Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad29ba01-d6f6-4f79-81d8-27dbcc28f206 · outbound

This paper cites Information-theoretic considerations in batch reinforcement learning.

Scaling Automatic Research Agents via World Models Information-theoretic considerations in batch reinforcement learning

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-16T00:11:05.586199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29769821-e6f9-413b-bcec-bb1e428d6043 · outbound

This paper cites Risk bounds in isotonic regression.The Annals of Statistics, 30(2):528–555, 2002.

Scaling Automatic Research Agents via World Models Risk bounds in isotonic regression.The Annals of Statistics, 30(2):528–555, 2002

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:11:06.343549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 16bd80b9-5de1-41a1-953c-0cea028cb6e2 · outbound

This paper cites MLE-bench: Evaluating machine learning agents on machine learning engineering.https: //openai.com/index/mle-bench/, 2024.

Scaling Automatic Research Agents via World Models MLE-bench: Evaluating machine learning agents on machine learning engineering.https: //openai.com/index/mle-bench/, 2024

Reference 66

Resolution: malformed identifier; raw_fallback, observed 2026-08-16T00:11:06.327646Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation e4c22bb7-b518-4a2e-befc-c756a43a7fa6 · outbound

This paper cites an unresolved cited work.

Scaling Automatic Research Agents via World Models Unresolved cited work

Reference 67

Resolution: unresolved; raw_fallback, observed 2026-08-16T00:11:06.311940Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 951cc6cd-d94c-4e8e-aaf0-73d90dbd9126 · outbound

This paper cites reason":.

Scaling Automatic Research Agents via World Models reason":

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:11:06.297389Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers