Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-05-10T19:27:42.198509Z
Paper Citation Record · LEDGER
RAGEN-2: Reasoning Collapse in Agentic RL
As of 6 August 2026, this Paper Citation Record lists 74 of 74 outbound references and 5 inbound Pith citation observations for arXiv:2604.06268.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-05T06:32:48.257954+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-04T15:25:49.276550Z
A source-named dated measurement, never combined with another source.
Source: pith, observed 2026-07-02T02:56:29.103440Z
Reference resolution
74 of 74 outbound references displayed
- verified exact4
- verified fuzzy66
- unresolved4
- parse uncertain0
- malformed identifier0
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 28350cce-a2f6-45e1-a12f-13a64501affc · outbound
This paper cites Qwen2.5-vl technical report.
RAGEN-2: Reasoning Collapse in Agentic RL Qwen2.5-vl technical report
Reference 1
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.743796Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation eaae6871-6ef0-4989-a084-0cfe18ed64c6 · outbound
This paper cites Openai gym.
RAGEN-2: Reasoning Collapse in Agentic RL Openai gym
Reference 2
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.797017Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 667e742a-5e98-4cfc-bd6d-c42f44c52228 · outbound
This paper cites Internalizing world models via self-play finetuning for agentic rl.
RAGEN-2: Reasoning Collapse in Agentic RL Internalizing world models via self-play finetuning for agentic rl
Reference 3
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.904757Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 5e01b4e1-8742-42b3-b380-69c363552ae1 · outbound
This paper cites Training verifiers to solve math word problems.
RAGEN-2: Reasoning Collapse in Agentic RL Training verifiers to solve math word problems
Reference 4
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.842690Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 8adeb1ac-34a6-4a3a-b811-56efb34d90e5 · outbound
This paper cites Cover and Joy A.
RAGEN-2: Reasoning Collapse in Agentic RL Cover and Joy A
Reference 5
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.877149Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation dfa673ed-023d-4c3b-b16b-4f531b981b0b · outbound
This paper cites Process reinforcement through implicit rewards.
RAGEN-2: Reasoning Collapse in Agentic RL Process reinforcement through implicit rewards
Reference 6
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.873821Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 942028a7-91a8-49af-b5c8-dedaf440765c · outbound
This paper cites Deepseek-r1 incentivizes reasoning in llms through reinforcement learning.Nature, 645(8081):633–638, September 2025.
RAGEN-2: Reasoning Collapse in Agentic RL Deepseek-r1 incentivizes reasoning in llms through reinforcement learning.Nature, 645(8081):633–638, September 2025
Reference 7
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.874284Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation ffe4d188-fb6a-41a4-b7de-8821c07f48e1 · outbound
This paper cites Re-rest: Reflection- reinforced self-training for language agents.
RAGEN-2: Reasoning Collapse in Agentic RL Re-rest: Reflection- reinforced self-training for language agents
Reference 8
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.832804Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation e5192c36-3a02-42e3-b73c-180a678672e7 · outbound
This paper cites Group-in-group policy optimization for llm agent training.
RAGEN-2: Reasoning Collapse in Agentic RL Group-in-group policy optimization for llm agent training
Reference 9
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.897656Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation ffff3b51-4bdc-4992-b80a-dd7c89b73f8d · outbound
This paper cites Dory: Deliberative prompt recovery for llm.
RAGEN-2: Reasoning Collapse in Agentic RL Dory: Deliberative prompt recovery for llm
Reference 10
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.879894Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 515b2649-604a-4830-91dd-ba17cab3b37d · outbound
This paper cites Liu, Phoebe Mulcaire, Qiang Ning, Sameer Singh, Noah A.
RAGEN-2: Reasoning Collapse in Agentic RL Liu, Phoebe Mulcaire, Qiang Ning, Sameer Singh, Noah A
Reference 11
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.728392Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 89703a0a-6b2d-472e-8b81-6f88374f065b · outbound
This paper cites Roberts, Diyi Yang, David L.
RAGEN-2: Reasoning Collapse in Agentic RL Roberts, Diyi Yang, David L
Reference 12
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.766484Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 18b6b94f-c114-4979-94b8-63ac0afcfa4d · outbound
This paper cites Soft actor-critic algorithms and applications.
RAGEN-2: Reasoning Collapse in Agentic RL Soft actor-critic algorithms and applications
Reference 13
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.851415Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 1b4b231c-1a63-44fd-9d56-b19da856118e · outbound
This paper cites The curious case of neural text degeneration.
RAGEN-2: Reasoning Collapse in Agentic RL The curious case of neural text degeneration
Reference 14
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.823491Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation bfe2841a-a4a0-4e75-be34-8bb3c0e299b5 · outbound
This paper cites LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code.
RAGEN-2: Reasoning Collapse in Agentic RL LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
Reference 15
- Resolution
- verified exact
- local_arxiv, observed 2026-05-10T22:55:51.538353Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 68f63be9-2e1f-485d-8a3f-d38f8dfa106e · outbound
This paper cites Benchmarking llms on the game of countdown.
RAGEN-2: Reasoning Collapse in Agentic RL Benchmarking llms on the game of countdown
Reference 16
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.762755Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation edb8b3ed-7af7-450e-9cb0-0b17cd7d0ef2 · outbound
This paper cites Understanding the effects of rlhf on llm generalisation and diversity.
RAGEN-2: Reasoning Collapse in Agentic RL Understanding the effects of rlhf on llm generalisation and diversity
Reference 17
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.919768Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 9364c30f-0855-4944-acee-e1340709ba86 · outbound
This paper cites Bowman, and Ethan Perez.
RAGEN-2: Reasoning Collapse in Agentic RL Bowman, and Ethan Perez
Reference 18
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.835710Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation cc66986d-21ac-45b6-a4dd-33d1fc572ec6 · outbound
This paper cites Reverse prompt engineering.
RAGEN-2: Reasoning Collapse in Agentic RL Reverse prompt engineering
Reference 19
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.802191Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation b3cbed5b-75be-4203-80a6-b894154de3ed · outbound
This paper cites A diversity-promoting objective function for neural conversation models.
RAGEN-2: Reasoning Collapse in Agentic RL A diversity-promoting objective function for neural conversation models
Reference 20
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.789941Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 9a0900a7-e352-4f55-b8cf-dc998bf08ad3 · outbound
This paper cites TACO: Topics in Algorithmic COde generation dataset.
RAGEN-2: Reasoning Collapse in Agentic RL TACO: Topics in Algorithmic COde generation dataset
Reference 21
- Resolution
- verified exact
- arxiv_id, observed 2026-05-10T22:55:51.524084Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 6dc0a013-d290-4c5e-af0a-3f3dbf416d94 · outbound
This paper cites Unary feedback as observation: Incentivizing self-reflection in large language models via multi-turn RL.
RAGEN-2: Reasoning Collapse in Agentic RL Unary feedback as observation: Incentivizing self-reflection in large language models via multi-turn RL
Reference 22
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.712499Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation d0029fed-1c08-470f-a5d9-445481ff4df2 · outbound
This paper cites Understanding r1-zero-like training: A critical perspective.
RAGEN-2: Reasoning Collapse in Agentic RL Understanding r1-zero-like training: A critical perspective
Reference 23
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.756494Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 9c176b54-51d2-4dac-9ad3-0bce6323706b · outbound
This paper cites Self-refine: Iterative refinement with self-feedback.
RAGEN-2: Reasoning Collapse in Agentic RL Self-refine: Iterative refinement with self-feedback
Reference 24
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.885392Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 3944c950-2199-47e0-9146-7ef30a0ff7cc · outbound
This paper cites Synthetic-1: Two million collaboratively generated reasoning traces from deepseek-r1.
RAGEN-2: Reasoning Collapse in Agentic RL Synthetic-1: Two million collaboratively generated reasoning traces from deepseek-r1
Reference 25
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.793890Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation d309c8d8-759b-4371-825b-a6b2fc18799b · outbound
This paper cites Llama 3.2 3b model card.
RAGEN-2: Reasoning Collapse in Agentic RL Llama 3.2 3b model card
Reference 26
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.867406Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation a7d702ab-89a6-4d46-b104-8f2def1f19ed · outbound
This paper cites Jointly measuring diversity and quality in text generation models.
RAGEN-2: Reasoning Collapse in Agentic RL Jointly measuring diversity and quality in text generation models
Reference 27
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.816282Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 41d6b46c-a190-49dd-970c-e348cf7aac60 · outbound
This paper cites Morris, Wenting Zhao, Justin T.
RAGEN-2: Reasoning Collapse in Agentic RL Morris, Wenting Zhao, Justin T
Reference 28
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.867628Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation fd6a84d4-dccc-4a72-88a9-5fe80f16151b · outbound
This paper cites Singh, DJ Strouse, Tuomas Sandholm, Ruslan Salakhutdinov, Anca D.
RAGEN-2: Reasoning Collapse in Agentic RL Singh, DJ Strouse, Tuomas Sandholm, Ruslan Salakhutdinov, Anca D
Reference 29
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.779894Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 2cfaca5c-e74f-43c7-bfab-809e0e676dce · outbound
This paper cites Webgpt: Browser-assisted question-answering with human feedback.
RAGEN-2: Reasoning Collapse in Agentic RL Webgpt: Browser-assisted question-answering with human feedback
Reference 30
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.822542Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation b9c116d0-5a1d-46ad-aabd-58640870efaf · outbound
This paper cites Attributing mode collapse in the fine-tuning of large language models.
RAGEN-2: Reasoning Collapse in Agentic RL Attributing mode collapse in the fine-tuning of large language models
Reference 31
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.888268Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation ac29c65a-ee4c-4e27-9764-eb7871567b04 · outbound
This paper cites an unresolved cited work.
RAGEN-2: Reasoning Collapse in Agentic RL Unresolved cited work
Reference 32
- Resolution
- unresolved
- raw_fallback, observed 2026-05-16T05:00:37.799373Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation dad2f4a7-85bf-400a-a4a5-99fbf01f1ade · outbound
This paper cites Mauve: Measuring the gap between neural text and human text using divergence frontiers.
RAGEN-2: Reasoning Collapse in Agentic RL Mauve: Measuring the gap between neural text and human text using divergence frontiers
Reference 33
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.812795Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 6b9efedf-aead-4e3f-876a-3445a881bf61 · outbound
This paper cites Defeating the training-inference mismatch via fp16.
RAGEN-2: Reasoning Collapse in Agentic RL Defeating the training-inference mismatch via fp16
Reference 34
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.834955Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 98b85036-4d88-4796-a66c-25cfa340cf0b · outbound
This paper cites Qwen2.5 technical report.
RAGEN-2: Reasoning Collapse in Agentic RL Qwen2.5 technical report
Reference 35
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.860910Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 2d1d1625-224d-4321-881a-40ada8be893e · outbound
This paper cites Manning, and Chelsea Finn.
RAGEN-2: Reasoning Collapse in Agentic RL Manning, and Chelsea Finn
Reference 36
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.776463Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 653adb4e-4415-407e-b775-9916d5a275cb · outbound
This paper cites Beyond accuracy: Behavioral testing of nlp models with checklist.
RAGEN-2: Reasoning Collapse in Agentic RL Beyond accuracy: Behavioral testing of nlp models with checklist
Reference 37
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.882537Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation ab38c871-57ca-4625-a210-075ae3ce6310 · outbound
This paper cites Reward estimation for variance reduction in deep reinforcement learning.
RAGEN-2: Reasoning Collapse in Agentic RL Reward estimation for variance reduction in deep reinforcement learning
Reference 38
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.746531Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 1da224ad-3907-4857-b57f-8cb04dd6dc27 · outbound
This paper cites Schrader.
Reference 39
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.876073Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 0e89ac8c-73e1-4030-80a0-03558b6001ba · outbound
This paper cites Jordan, and Pieter Abbeel.
RAGEN-2: Reasoning Collapse in Agentic RL Jordan, and Pieter Abbeel
Reference 40
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.850039Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 96f2afde-b243-4e78-bf4f-cb13574ddb50 · outbound
This paper cites High-dimensional continuous control using generalized advantage estimation.
RAGEN-2: Reasoning Collapse in Agentic RL High-dimensional continuous control using generalized advantage estimation
Reference 41
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.871349Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation ff72a49d-ba72-4284-8eda-e4f2d4603bf7 · outbound
This paper cites Proximal policy optimization algorithms.
RAGEN-2: Reasoning Collapse in Agentic RL Proximal policy optimization algorithms
Reference 42
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.838717Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation f034535e-6dbd-4eb7-bacd-c57d02cf28c2 · outbound
This paper cites On accurate evaluation of gans for language generation.
RAGEN-2: Reasoning Collapse in Agentic RL On accurate evaluation of gans for language generation
Reference 43
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.907882Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 97dc48a3-2ca1-412b-b813-b058fc34a4f0 · outbound
This paper cites an unresolved cited work.
RAGEN-2: Reasoning Collapse in Agentic RL Unresolved cited work
Reference 44
- Resolution
- unresolved
- raw_fallback, observed 2026-05-16T05:00:37.842025Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 8e53d5eb-a7d9-4aa0-b3c0-9de558d906f8 · outbound
This paper cites Hybridflow: A flexible and efficient rlhf framework.
RAGEN-2: Reasoning Collapse in Agentic RL Hybridflow: A flexible and efficient rlhf framework
Reference 45
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.787448Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 3af635df-1b95-471d-8ab3-98f2db5ca5b2 · outbound
This paper cites Reflexion: Language agents with verbal reinforcement learning.
RAGEN-2: Reasoning Collapse in Agentic RL Reflexion: Language agents with verbal reinforcement learning
Reference 46
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.819947Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 0c9feb05-51cc-43c7-b265-9dc00fce30b4 · outbound
This paper cites Ai models collapse when trained on recursively generated data.Nature, 631:755–759.
RAGEN-2: Reasoning Collapse in Agentic RL Ai models collapse when trained on recursively generated data.Nature, 631:755–759
Reference 47
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.728598Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 7bd00825-62a2-4618-905d-dee8a2aba694 · outbound
This paper cites Siegel, Oana-Maria Camburu, Nicolas Heess, and Maria Perez-Ortiz.
RAGEN-2: Reasoning Collapse in Agentic RL Siegel, Oana-Maria Camburu, Nicolas Heess, and Maria Perez-Ortiz
Reference 48
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.894651Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 4a9248ec-21e2-4858-b871-498d88ed116f · outbound
This paper cites Ziegler, Ryan Lowe, Chelsea Voss, Alec Radford, Dario Amodei, and Paul Christiano.
RAGEN-2: Reasoning Collapse in Agentic RL Ziegler, Ryan Lowe, Chelsea Voss, Alec Radford, Dario Amodei, and Paul Christiano
Reference 49
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.731328Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 124c9268-97a6-4a03-86d9-6ba8f1e3ac54 · outbound
This paper cites Fast best-of-n decoding via speculative rejection.
RAGEN-2: Reasoning Collapse in Agentic RL Fast best-of-n decoding via speculative rejection
Reference 50
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.864770Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 2295f0d7-5046-4de1-95e8-82635d402912 · outbound
This paper cites rllm: A framework for post-training language agents.
RAGEN-2: Reasoning Collapse in Agentic RL rllm: A framework for post-training language agents
Reference 51
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.765508Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 1808a71a-70bf-4c7e-9c75-f9cf3e295a30 · outbound
This paper cites Hybrid reinforcement: When reward is sparse, it’s better to be dense.
RAGEN-2: Reasoning Collapse in Agentic RL Hybrid reinforcement: When reward is sparse, it’s better to be dense
Reference 52
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.838529Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 82ff4542-a2b4-4371-8c5c-c369a89f5db2 · outbound
This paper cites Evaluating the evaluation of diversity in natural language genera- tion.
RAGEN-2: Reasoning Collapse in Agentic RL Evaluating the evaluation of diversity in natural language genera- tion
Reference 53
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.891424Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation bafa2753-42b4-4461-bde8-2efba96bcc77 · outbound
This paper cites an unresolved cited work.
RAGEN-2: Reasoning Collapse in Agentic RL Unresolved cited work
Reference 54
- Resolution
- unresolved
- raw_fallback, observed 2026-05-16T05:00:37.770073Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation fb82b083-79c3-4b25-8a22-95616d530e23 · outbound
This paper cites Solving math word problems with process- and outcome-based feedback.
RAGEN-2: Reasoning Collapse in Agentic RL Solving math word problems with process- and outcome-based feedback
Reference 55
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.756834Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 5f5488e3-7c61-4f4d-8107-fb476a744b85 · outbound
This paper cites Voyager: An open-ended embodied agent with large language models.
RAGEN-2: Reasoning Collapse in Agentic RL Voyager: An open-ended embodied agent with large language models
Reference 56
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.861572Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation c7cb231c-bb82-4ab8-a49e-2e76ccf20d96 · outbound
This paper cites Harnessing uncertainty: Entropy-modulated policy gradients for long-horizon llm agents.
RAGEN-2: Reasoning Collapse in Agentic RL Harnessing uncertainty: Entropy-modulated policy gradients for long-horizon llm agents
Reference 57
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.740876Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 245d5148-d44e-41f0-b01b-fdc039959c43 · outbound
This paper cites Vagen: Reinforcingworldmodelreasoningformulti-turnvlm agents.arXivpreprint.
RAGEN-2: Reasoning Collapse in Agentic RL Vagen: Reinforcingworldmodelreasoningformulti-turnvlm agents.arXivpreprint
Reference 58
- Resolution
- verified exact
- arxiv_id, observed 2026-05-10T22:55:51.516784Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 7d663f49-0723-4d8f-8bd7-4cca1e51fd1d · outbound
This paper cites A practitioner’s guide to multi-turn agentic reinforcement learning.
RAGEN-2: Reasoning Collapse in Agentic RL A practitioner’s guide to multi-turn agentic reinforcement learning
Reference 59
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.901608Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 1a2712bc-3699-45bf-836b-ee70f80acad5 · outbound
This paper cites Ragen: Understanding self-evolution in llm agents via multi-turn reinforcement learning.
RAGEN-2: Reasoning Collapse in Agentic RL Ragen: Understanding self-evolution in llm agents via multi-turn reinforcement learning
Reference 60
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.857779Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation b17b9b18-a658-493b-b972-ec0bab70dc6d · outbound
This paper cites Gtr: Guided thought reinforcement prevents thought collapse in rl-based vlm agent training.
RAGEN-2: Reasoning Collapse in Agentic RL Gtr: Guided thought reinforcement prevents thought collapse in rl-based vlm agent training
Reference 61
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.737996Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 6fa3dcc2-46b9-49f9-8e69-d37b017dccad · outbound
This paper cites an unresolved cited work.
RAGEN-2: Reasoning Collapse in Agentic RL Unresolved cited work
Reference 62
- Resolution
- unresolved
- raw_fallback, observed 2026-05-16T05:00:37.848245Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation f6d32405-37c1-4d19-b4c0-4a50a1df3bbc · outbound
This paper cites Diversity-aware policy optimization for large language model reasoning.
RAGEN-2: Reasoning Collapse in Agentic RL Diversity-aware policy optimization for large language model reasoning
Reference 63
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.819505Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 43fd0d40-c438-4899-ac70-0ff80ff8f4d0 · outbound
This paper cites Webshop: Towards scalable real- world web interaction with grounded language agents.
RAGEN-2: Reasoning Collapse in Agentic RL Webshop: Towards scalable real- world web interaction with grounded language agents
Reference 64
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.857918Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 019452a4-6505-4619-aa2a-f47641e8ca58 · outbound
This paper cites React: Synergizing reasoning and acting in language models.
RAGEN-2: Reasoning Collapse in Agentic RL React: Synergizing reasoning and acting in language models
Reference 65
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.914028Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 78ba6300-3aad-41ea-9f3a-fe31e9b7d37f · outbound
This paper cites Spa- tial mental modeling from limited views.
RAGEN-2: Reasoning Collapse in Agentic RL Spa- tial mental modeling from limited views
Reference 66
- Resolution
- verified exact
- arxiv_id, observed 2026-05-10T22:55:51.503835Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 284e55e5-0cea-4a04-b6f2-5a635979638d · outbound
This paper cites Kwok, Zhenguo Li, Adrian Weller, and Weiyang Liu.
RAGEN-2: Reasoning Collapse in Agentic RL Kwok, Zhenguo Li, Adrian Weller, and Weiyang Liu
Reference 67
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.796360Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation b50e34d4-1e8f-4d5d-b12b-07ba750ab561 · outbound
This paper cites Dapo: An open-source llm reinforcement learning system at scale.
RAGEN-2: Reasoning Collapse in Agentic RL Dapo: An open-source llm reinforcement learning system at scale
Reference 68
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.809935Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation a21959a5-ba96-45c9-a512-e4240ed80656 · outbound
This paper cites The price of format: Diversity collapse in llms.
RAGEN-2: Reasoning Collapse in Agentic RL The price of format: Diversity collapse in llms
Reference 69
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.916766Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation e1b9ce37-610a-44ae-9976-02fcebbcc5c1 · outbound
This paper cites Is chain-of-thought really not explainability? chain-of- thought can be faithful without hint verbalization.
RAGEN-2: Reasoning Collapse in Agentic RL Is chain-of-thought really not explainability? chain-of- thought can be faithful without hint verbalization
Reference 70
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.722347Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation b368af65-782b-4e84-9614-09aba062f739 · outbound
This paper cites Morris, and Vitaly Shmatikov.
RAGEN-2: Reasoning Collapse in Agentic RL Morris, and Vitaly Shmatikov
Reference 71
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.854451Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation d8d8ba7f-a28e-4869-8367-9f6bed2359f1 · outbound
This paper cites Beyond precision: Training-inference mismatch is an optimization problem and simple lr scheduling fixes it.
RAGEN-2: Reasoning Collapse in Agentic RL Beyond precision: Training-inference mismatch is an optimization problem and simple lr scheduling fixes it
Reference 72
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.702798Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 7554ff2f-0dea-4fb7-8493-b75e10370b68 · outbound
This paper cites Promptbench: A unified library for evaluation of large language models.
RAGEN-2: Reasoning Collapse in Agentic RL Promptbench: A unified library for evaluation of large language models
Reference 73
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.910974Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 3e4332b2-2576-4e0c-9ecc-43f8d1ab0810 · outbound
This paper cites Countdown.
Reference 74
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-16T05:00:37.749880Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Pith citing papers
Observation 31b22a26-b089-4d9d-81b5-54ee2e38cf85 · inbound
Signal Reshaping for GRPO in Weak-Feedback Agentic Code Repair cites this paper.
Signal Reshaping for GRPO in Weak-Feedback Agentic Code Repair RAGEN-2: Reasoning Collapse in Agentic RL
Reference 44
- Resolution
- verified exact
- local_arxiv, observed 2026-05-11T04:25:59.115847Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation c38e00c7-6d92-490b-a5d3-a8e1d7fb2ceb · inbound
Agent Explorative Policy Optimization for Multimodal Agentic Reasoning cites this paper.
Agent Explorative Policy Optimization for Multimodal Agentic Reasoning RAGEN-2: Reasoning Collapse in Agentic RL
Reference 37
- Resolution
- verified exact
- local_arxiv, observed 2026-06-29T12:23:24.161662Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation b6466a17-bf3a-442d-9222-54bb04b8c50d · inbound
EvoTrainer: Co-Evolving LLM Policies and Training Harnesses for Autonomous Agentic Reinforcement Learning cites this paper.
EvoTrainer: Co-Evolving LLM Policies and Training Harnesses for Autonomous Agentic Reinforcement Learning RAGEN-2: Reasoning Collapse in Agentic RL
Reference 63
- Resolution
- verified exact
- local_arxiv, observed 2026-07-02T02:56:29.105430Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation e2305126-e912-4ecb-8e5c-b2975f885fa4 · inbound
Agent Reinforcement Learning via Pivotal-Aware Self-Feedback Retry cites this paper.
Agent Reinforcement Learning via Pivotal-Aware Self-Feedback Retry RAGEN-2: Reasoning Collapse in Agentic RL
Reference 14
- 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 1be6bbd0-3f31-4d5a-a3e2-5382b62419c7 · inbound
Instruction-Conditioned Exploration with Asymmetric Reinforcement Learning and Self-Distillation cites this paper.
Instruction-Conditioned Exploration with Asymmetric Reinforcement Learning and Self-Distillation RAGEN-2: Reasoning Collapse in Agentic RL
Reference 18
- Resolution
- unresolved
- no resolver link, observed 2026-08-04T15:25:49.276550Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.