Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-06-27T01:19:55.164835Z
Paper Citation Record · LEDGER
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models
As of 4 August 2026, this Paper Citation Record lists 63 of 63 outbound references and 0 inbound Pith citation observations for arXiv:2606.17890.
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 2026-08-04T06:34:03.388597+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links
A source-named dated measurement, never combined with another source.
Source: cited_works
Reference resolution
63 of 63 outbound references displayed
- verified exact31
- verified fuzzy0
- unresolved25
- parse uncertain0
- malformed identifier0
- metadata mismatch7
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 19af4c52-33ce-42b9-81b5-cde8d0740526 · outbound
This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
Reference 1
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-06-27T01:20:20.417002Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation dad79881-0cd5-4ff8-8ac1-4679e8b2ec71 · outbound
This paper cites Nature , volume =.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models Nature , volume =
Reference 2
- Resolution
- unresolved
- no resolver link, observed 2026-06-27T01:19:55.164835Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4e825fd0-57ff-4e37-925d-a85ebce1b320 · outbound
This paper cites OpenAI o1 System Card.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models OpenAI o1 System Card
Reference 3
- Resolution
- verified exact
- local_arxiv, observed 2026-06-27T01:20:20.466847Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 1a824276-315b-4efa-821d-de3b518bc006 · outbound
This paper cites Qwen3 Technical Report.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models Qwen3 Technical Report
Reference 4
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-03T20:28:55.672673Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation f026f964-c5be-4ae9-a483-802765abe360 · outbound
This paper cites 2025 , month =.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models 2025 , month =
Reference 5
- Resolution
- unresolved
- no resolver link, observed 2026-06-27T01:19:55.164835Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8eb7da15-fae3-4903-99e1-a21da45fda28 · outbound
This paper cites A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?
Reference 6
- Resolution
- verified exact
- local_arxiv, observed 2026-06-27T01:20:20.424956Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 9cde0d36-7585-4f9a-a4ab-d2b522e4f35a · outbound
This paper cites From System 1 to System 2: A Survey of Reasoning Large Language Models.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models From System 1 to System 2: A Survey of Reasoning Large Language Models
Reference 7
- Resolution
- verified exact
- local_arxiv, observed 2026-06-27T01:20:20.479970Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 3baafb09-be1c-4d2a-9faf-7491f3bf1ee3 · outbound
This paper cites Stop Overthinking:.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models Stop Overthinking:
Reference 8
- Resolution
- unresolved
- no resolver link, observed 2026-06-27T01:19:55.164835Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e1e0ba81-caca-453c-8cbb-93274f58aa9d · outbound
This paper cites Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models
Reference 9
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-06-27T01:20:20.407741Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation b962f982-3edd-4d66-9356-c796f94b344b · outbound
This paper cites Distilling System 2 into System 1.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models Distilling System 2 into System 1
Reference 10
- Resolution
- verified exact
- arxiv_id, observed 2026-06-27T01:20:20.448324Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 928c4a76-0e7a-4c4e-9943-a38a3637f8cd · outbound
This paper cites AAAI-25, Sponsored by the Association for the Advancement of Artificial Intelligence, February 25 - March 4, 2025, Philadelphia, PA,.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models AAAI-25, Sponsored by the Association for the Advancement of Artificial Intelligence, February 25 - March 4, 2025, Philadelphia, PA,
Reference 11
- Resolution
- verified exact
- doi, observed 2026-06-27T01:20:20.419589Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 7b2357ed-6a3c-403f-aeeb-0b8233a6b20c · outbound
This paper cites Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing , year =.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing , year =
Reference 12
- Resolution
- unresolved
- no resolver link, observed 2026-06-27T01:19:55.164835Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5368e969-2474-456d-a6cc-5d5eab2a9724 · outbound
This paper cites Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , year =.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , year =
Reference 13
- Resolution
- unresolved
- no resolver link, observed 2026-06-27T01:19:55.164835Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b64f57a9-5df5-45d7-8af4-5ffd85f7e1db · outbound
This paper cites Can Language Models Learn to Skip Steps? , booktitle =.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models Can Language Models Learn to Skip Steps? , booktitle =
Reference 14
- Resolution
- unresolved
- no resolver link, observed 2026-06-27T01:19:55.164835Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 051c7cd6-0507-4e99-b240-0c40e6847112 · outbound
This paper cites Kimi k1.5: Scaling Reinforcement Learning with LLMs.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models Kimi k1.5: Scaling Reinforcement Learning with LLMs
Reference 15
- Resolution
- verified exact
- local_arxiv, observed 2026-06-27T01:20:20.458337Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 66a84732-3d1d-47bf-abed-772c10a71ce1 · outbound
This paper cites O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning
Reference 16
- Resolution
- verified exact
- arxiv_id, observed 2026-06-27T01:20:20.477310Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 10b2fc23-8611-434a-9926-6419f25d6a85 · outbound
This paper cites Second Conference on Language Modeling , year =.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models Second Conference on Language Modeling , year =
Reference 17
- Resolution
- unresolved
- no resolver link, observed 2026-06-27T01:19:55.164835Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fc63ee45-7a8f-497a-9280-54a85dfc5e07 · outbound
This paper cites Weston and Yuandong Tian , title =.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models Weston and Yuandong Tian , title =
Reference 18
- Resolution
- unresolved
- no resolver link, observed 2026-06-27T01:19:55.164835Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3b74bfb3-6c72-490d-975d-c86454c660e4 · outbound
This paper cites Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing , year =.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing , year =
Reference 19
- Resolution
- unresolved
- no resolver link, observed 2026-06-27T01:19:55.164835Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 34908b32-4c0c-4a7a-a55f-972cf9fe749f · outbound
This paper cites Compressed Chain of Thought: Efficient Reasoning Through Dense Representations.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models Compressed Chain of Thought: Efficient Reasoning Through Dense Representations
Reference 20
- Resolution
- verified exact
- local_arxiv, observed 2026-06-27T01:20:20.488804Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 78ceec20-2394-4e8b-8ef6-c20aa9a7a53b · outbound
This paper cites s1: Simple test-time scaling.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models s1: Simple test-time scaling
Reference 21
- Resolution
- verified exact
- local_arxiv, observed 2026-06-27T01:20:20.472173Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 8ba32e1b-27d5-401b-9136-70e8aa103061 · outbound
This paper cites Token-budget-aware LLM reasoning.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models Token-budget-aware LLM reasoning
Reference 22
- Resolution
- verified exact
- doi, observed 2026-06-27T01:20:20.440299Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 94a043c8-4983-4d23-a67b-97e9b9be399f · outbound
This paper cites How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach
Reference 23
- Resolution
- verified exact
- arxiv_id, observed 2026-06-27T01:20:20.433389Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 2208c267-3661-479a-91fa-1ec6c1a8c73c · outbound
This paper cites Reasoning Models Can Be Effective Without Thinking.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models Reasoning Models Can Be Effective Without Thinking
Reference 24
- Resolution
- verified exact
- arxiv_id, observed 2026-06-27T01:20:20.410691Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 821f09f2-014f-4f52-908d-b527c50a65ca · outbound
This paper cites ICLR 2025 Workshop on Foundation Models in the Wild , year=.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models ICLR 2025 Workshop on Foundation Models in the Wild , year=
Reference 25
- Resolution
- unresolved
- no resolver link, observed 2026-06-27T01:19:55.164835Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation dd00c702-9405-42d4-9e44-32d499c17dd2 · outbound
This paper cites Seal: Steerable reasoning calibration of large language models for free.arXiv preprint arXiv:2504.07986, 2025a.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models Seal: Steerable reasoning calibration of large language models for free.arXiv preprint arXiv:2504.07986, 2025a
Reference 26
- Resolution
- verified exact
- arxiv_id, observed 2026-06-27T01:20:20.442980Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation c69b05d2-50f6-40a5-9a9a-44f704b3b9ca · outbound
This paper cites The Fourteenth International Conference on Learning Representations,.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models The Fourteenth International Conference on Learning Representations,
Reference 27
- Resolution
- unresolved
- no resolver link, observed 2026-06-27T01:19:55.164835Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation bccb366f-1943-4c80-a936-05b7423a85bf · outbound
This paper cites 2025 , eprint=.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models 2025 , eprint=
Reference 28
- Resolution
- unresolved
- no resolver link, observed 2026-06-27T01:19:55.164835Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 130a2e5d-78a2-4b78-8107-b402bbf2b606 · outbound
This paper cites The Fourteenth International Conference on Learning Representations,.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models The Fourteenth International Conference on Learning Representations,
Reference 29
- Resolution
- unresolved
- no resolver link, observed 2026-06-27T01:19:55.164835Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b938dcb8-f066-4242-aec9-db628bc12bbf · outbound
This paper cites Answer convergence as a signal for early stopping in reasoning.arXiv preprint arXiv:2506.02536.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models Answer convergence as a signal for early stopping in reasoning.arXiv preprint arXiv:2506.02536
Reference 30
- Resolution
- verified exact
- arxiv_id, observed 2026-06-27T01:20:20.491283Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation d83e4d72-44a5-41a2-96ab-9d5af7a230b3 · outbound
This paper cites Advances in Neural Information Processing Systems , volume=.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models Advances in Neural Information Processing Systems , volume=
Reference 31
- Resolution
- unresolved
- no resolver link, observed 2026-06-27T01:19:55.164835Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0effb874-2f0a-469e-b734-8f1a5cd3b589 · outbound
This paper cites Does Your Reasoning Model Implicitly Know When to Stop Thinking?.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models Does Your Reasoning Model Implicitly Know When to Stop Thinking?
Reference 32
- Resolution
- verified exact
- local_arxiv, observed 2026-06-27T01:20:20.485987Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation f5629f6e-05b2-4f83-9aeb-45cf0d3c743d · outbound
This paper cites Proxythinker: Test-time guidance through small visual reasoners.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models Proxythinker: Test-time guidance through small visual reasoners
Reference 33
- Resolution
- verified exact
- arxiv_id, observed 2026-06-27T01:20:20.436395Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 122cc56d-829d-458e-a32b-598604d67000 · outbound
This paper cites arXiv preprint arXiv:2505.16142 , year =.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models arXiv preprint arXiv:2505.16142 , year =
Reference 34
- Resolution
- verified exact
- arxiv_id, observed 2026-06-27T01:20:20.482859Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 9d5f2695-ba0e-461e-abfe-036d6d9d4751 · outbound
This paper cites 2025 , eprint=.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models 2025 , eprint=
Reference 35
- Resolution
- unresolved
- no resolver link, observed 2026-06-27T01:19:55.164835Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a8040bf1-5352-4add-ad47-f6a9a7db81ba · outbound
This paper cites Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
Reference 36
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-06-27T01:20:20.474640Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 30463d4b-51c1-40e7-8dcb-95f70dc2b80d · outbound
This paper cites Forty-second International Conference on Machine Learning,.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models Forty-second International Conference on Machine Learning,
Reference 37
- Resolution
- unresolved
- no resolver link, observed 2026-06-27T01:19:55.164835Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9f9b1fce-5308-449c-9279-b3faeb261aff · outbound
This paper cites The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks
Reference 38
- Resolution
- verified exact
- arxiv_id, observed 2026-06-27T01:20:20.427621Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 87b9f984-2fe7-4fe4-800d-db18d699125a · outbound
This paper cites Bowman , booktitle =.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models Bowman , booktitle =
Reference 39
- Resolution
- unresolved
- no resolver link, observed 2026-06-27T01:19:55.164835Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 64850e6b-02cc-4e95-9a14-53db735465d2 · outbound
This paper cites The Thirteenth International Conference on Learning Representations,.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models The Thirteenth International Conference on Learning Representations,
Reference 40
- Resolution
- unresolved
- no resolver link, observed 2026-06-27T01:19:55.164835Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 875ab860-dfd0-49c9-bfff-14c4c2a17e71 · outbound
This paper cites CatBoost: gradient boosting with categorical features support.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models CatBoost: gradient boosting with categorical features support
Reference 41
- Resolution
- verified exact
- local_arxiv, observed 2026-07-03T20:28:55.670228Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 63cdcf28-7f01-4254-ac58-860ae92b80b5 · outbound
This paper cites Revisiting Overthinking in Long Chain-of-Thought from the Perspective of Self-Doubt.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models Revisiting Overthinking in Long Chain-of-Thought from the Perspective of Self-Doubt
Reference 42
- Resolution
- verified exact
- arxiv_id, observed 2026-06-27T01:20:20.430752Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 9c75a31b-a1b5-4f76-93b5-bce026bddc92 · outbound
This paper cites Reasoning Models Know When They're Right: Probing Hidden States for Self-Verification.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models Reasoning Models Know When They're Right: Probing Hidden States for Self-Verification
Reference 43
- Resolution
- verified exact
- arxiv_id, observed 2026-06-27T01:20:20.414019Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 915c136d-ffa7-4926-99a0-0c210dab04e4 · outbound
This paper cites Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics, Barcelona, Spain, July 21-26, 2004 - Poster and Demonstration , publisher =.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics, Barcelona, Spain, July 21-26, 2004 - Poster and Demonstration , publisher =
Reference 44
- Resolution
- unresolved
- no resolver link, observed 2026-06-27T01:19:55.164835Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d2fcfcb6-f5cd-4aae-803d-1a18f4f4f5dd · outbound
This paper cites Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models
Reference 45
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-06-27T01:20:20.460749Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation f6b8bc6c-820a-491e-a546-4a2bf05e08f7 · outbound
This paper cites Answer convergence as a signal for early stopping in reasoning.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models Answer convergence as a signal for early stopping in reasoning
Reference 46
- Resolution
- verified exact
- doi, observed 2026-06-27T01:20:20.451214Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation fc34335f-3fb4-4612-9a7f-d1a3610b2ccf · outbound
This paper cites Stop when enough: Adaptive early-stopping for chain-of-thought reasoning.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models Stop when enough: Adaptive early-stopping for chain-of-thought reasoning
Reference 47
- Resolution
- verified exact
- arxiv_id, observed 2026-06-27T01:20:20.455211Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 14627de6-5ed9-4683-92de-60bac275179f · outbound
This paper cites THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models
Reference 48
- Resolution
- verified exact
- arxiv_id, observed 2026-06-27T01:20:20.464479Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation b6be4521-cc61-4f29-ab5d-14c4c3bc7aa0 · outbound
This paper cites Introducing LongCat-flash-thinking: A technical report.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models Introducing LongCat-flash-thinking: A technical report
Reference 49
- Resolution
- verified exact
- arxiv_id, observed 2026-06-27T01:20:20.445767Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 1a1ccc34-5b04-4df7-adab-e8c470ae2c6c · outbound
This paper cites Proceedings of the AAAI Conference on Artificial Intelligence , volume =.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models Proceedings of the AAAI Conference on Artificial Intelligence , volume =
Reference 50
- Resolution
- unresolved
- no resolver link, observed 2026-06-27T01:19:55.164835Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 68f461a4-51ca-4079-8372-3c5f2e54d8b7 · outbound
This paper cites Advances in Neural Information Processing Systems , volume =.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models Advances in Neural Information Processing Systems , volume =
Reference 51
- Resolution
- unresolved
- no resolver link, observed 2026-06-27T01:19:55.164835Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3172a978-5950-4bcf-b0b8-41bff2d9b5b3 · outbound
This paper cites The Fourteenth International Conference on Learning Representations,.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models The Fourteenth International Conference on Learning Representations,
Reference 52
- Resolution
- unresolved
- no resolver link, observed 2026-06-27T01:19:55.164835Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fd03b8c5-8032-43ac-9176-5da1f969216c · outbound
This paper cites Between Underthinking and Overthinking: An Empirical Study of Reasoning Length and correctness in LLMs.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models Between Underthinking and Overthinking: An Empirical Study of Reasoning Length and correctness in LLMs
Reference 53
- Resolution
- verified exact
- arxiv_id, observed 2026-06-27T01:20:20.404474Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation fa8043a2-74ba-4037-a898-d80c21ac9bb2 · outbound
This paper cites The evolution of thought: Tracking llm overthinking via reasoning dynamics analysis.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models The evolution of thought: Tracking llm overthinking via reasoning dynamics analysis
Reference 54
- Resolution
- verified exact
- arxiv_id, observed 2026-06-27T01:20:20.394714Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 3844f17a-6ff0-4657-b60e-cb50109e83a7 · outbound
This paper cites arXiv preprint arXiv:2509.23024 , year=.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models arXiv preprint arXiv:2509.23024 , year=
Reference 55
- Resolution
- verified exact
- arxiv_id, observed 2026-06-27T01:20:20.379323Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 2793d116-fdcf-4db7-b403-7eb8c5a445a0 · outbound
This paper cites In NeurIPS 2025 Workshop on Foundations of Reasoning in Language Models (FoRLM).
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models In NeurIPS 2025 Workshop on Foundations of Reasoning in Language Models (FoRLM)
Reference 56
- Resolution
- verified exact
- arxiv_id, observed 2026-06-27T01:20:20.388880Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation eaa7aeff-abeb-4ed9-b411-a7e4a1cd06d9 · outbound
This paper cites The geometry of reasoning: Flowing logics in representation space.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models The geometry of reasoning: Flowing logics in representation space
Reference 57
- Resolution
- verified exact
- arxiv_id, observed 2026-06-27T01:20:20.391753Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 0f47999a-197d-4b56-abef-192d3bd6a512 · outbound
This paper cites Let's Verify Step by Step.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models Let's Verify Step by Step
Reference 58
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-03T20:28:55.674815Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 0c66043d-ab02-4817-ab44-633d04a7ee4d · outbound
This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
Reference 59
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-06-27T01:20:20.384992Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 85d85f9b-1ba0-4ff3-9f70-b9b0eb3345ad · outbound
This paper cites Advances in Neural Information Processing Systems , volume =.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models Advances in Neural Information Processing Systems , volume =
Reference 60
- Resolution
- unresolved
- no resolver link, observed 2026-06-27T01:19:55.164835Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 80c37040-d1ab-4db5-b4e1-35e7b39b70de · outbound
This paper cites an unresolved cited work.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models Unresolved cited work
Reference 61
- Resolution
- unresolved
- no resolver link, observed 2026-06-27T01:19:55.164835Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 722a1cb1-2076-40c3-a3f3-663b42a6ab7c · outbound
This paper cites Advances in Neural Information Processing Systems , volume =.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models Advances in Neural Information Processing Systems , volume =
Reference 62
- Resolution
- unresolved
- no resolver link, observed 2026-06-27T01:19:55.164835Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7de60c0a-a784-43eb-8721-f0f0428df11d · outbound
This paper cites CoRR , volume =.
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models CoRR , volume =
Reference 63
- Resolution
- verified exact
- arxiv_id, observed 2026-06-27T01:20:20.397961Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Pith citing papers
No inbound Pith citation observations are available.