Paper Citation Record · LEDGER

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models

As of 15 August 2026, this Paper Citation Record lists 94 of 94 outbound references and 3 inbound Pith citation observations for arXiv:2605.17672.

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

pith.paper-citation-record.v1
2605.17672 v1

Coverage vector

measured 94 of 94 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-20T12:29:30.505761Z

measured 97 of 97 standing notices

One-hop event checks from named stored sources.

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

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T07:51:14.115517Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

94 of 94 outbound references displayed

verified exact33
verified fuzzy52
unresolved3
parse uncertain0
malformed identifier1
metadata mismatch5

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation b60e8d8b-e6a5-4b97-83c0-69695129d845 · outbound

This paper cites Deepseek-r1 incentivizes reasoning in llms through reinforcement learning.Nature, 645(8081):633–638.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Deepseek-r1 incentivizes reasoning in llms through reinforcement learning.Nature, 645(8081):633–638

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T12:33:27.911032Z

Source-reported events for the cited work

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

Observation e1702212-4a14-4abd-ad31-75e10a58f742 · outbound

This paper cites OpenAI o1 System Card.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models OpenAI o1 System Card

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-05-20T12:33:17.054548Z

Source-reported events for the cited work

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

Observation 00634cca-3fdb-44a1-8133-79fe466af649 · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large language models.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Chain-of-thought prompting elicits reasoning in large language models

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T12:33:27.905309Z

Source-reported events for the cited work

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

Observation b245e15d-d2d1-418b-b478-35a218773b66 · outbound

This paper cites Stolfo, A., Balachandran, V ., Yousefi, S., Horvitz, E., and Nushi, B.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Stolfo, A., Balachandran, V ., Yousefi, S., Horvitz, E., and Nushi, B

Reference 4

Resolution: metadata mismatch; doi, observed 2026-05-20T12:33:16.705469Z

Source-reported events for the cited work

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

Observation 2be3e787-426d-4289-b12e-5514a8ead0ae · outbound

This paper cites an unresolved cited work.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-05-20T12:33:27.907238Z

Source-reported events for the cited work

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

Observation cdfb56d3-4929-4d07-8d60-9246ee06ffd5 · outbound

This paper cites Towards thinking-optimal scaling of test- time compute for LLM reasoning.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Towards thinking-optimal scaling of test- time compute for LLM reasoning

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T12:33:27.913228Z

Source-reported events for the cited work

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

Observation b481d3f8-41ea-4347-9858-7e888dd85f2c · outbound

This paper cites Qwen3 Technical Report.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Qwen3 Technical Report

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-05-20T12:33:17.061086Z

Source-reported events for the cited work

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

Observation 41291be0-3631-4a0a-83c8-3e9e639dfb78 · outbound

This paper cites Scaling llm test-time compute optimally can be more effective than scaling parameters for reasoning.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Scaling llm test-time compute optimally can be more effective than scaling parameters for reasoning

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T12:33:27.909085Z

Source-reported events for the cited work

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

Observation 4541e96e-4c36-4095-a05e-9b7643342e95 · outbound

This paper cites Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-20T14:19:45.019656Z

Source-reported events for the cited work

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

Observation 1b4ce616-87ea-439b-bf87-4cdac6a0d606 · outbound

This paper cites How far are we from optimal reasoning efficiency? InThe Thirty-ninth Annual Conference on Neural Information Processing Systems.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models How far are we from optimal reasoning efficiency? InThe Thirty-ninth Annual Conference on Neural Information Processing Systems

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T12:33:27.866107Z

Source-reported events for the cited work

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

Observation 36d20faa-4c6e-4ce6-ab15-25fdcd4d949d · outbound

This paper cites TL;DR: Too Long, Do Re-weighting for Efficient LLM Reasoning Compression.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models TL;DR: Too Long, Do Re-weighting for Efficient LLM Reasoning Compression

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-20T12:33:17.035460Z

Source-reported events for the cited work

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

Observation 4239e332-9829-44a3-9f1a-c9779b4a38eb · outbound

This paper cites Language agent tree search unifies reasoning, acting, and planning in language models.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Language agent tree search unifies reasoning, acting, and planning in language models

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T12:33:27.882661Z

Source-reported events for the cited work

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

Observation c9cb33ec-6ee0-43df-bfa9-117c06814bff · outbound

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

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models React: Synergizing reasoning and acting in language models

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T12:33:27.903425Z

Source-reported events for the cited work

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

Observation a9bc0650-0a8b-4011-93e7-72811fd95119 · outbound

This paper cites Group Think: Multiple Concurrent Reasoning Agents Collaborating at Token Level Granularity.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Group Think: Multiple Concurrent Reasoning Agents Collaborating at Token Level Granularity

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-20T12:33:17.041567Z

Source-reported events for the cited work

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

Observation e65a76b5-6745-46b5-b2d1-199edfc8f67b · outbound

This paper cites Phgpo: Pheromone-guided policy optimization for long-horizon tool planning.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Phgpo: Pheromone-guided policy optimization for long-horizon tool planning

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-20T12:33:17.038440Z

Source-reported events for the cited work

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

Observation e5bd01be-abf1-41fa-81ae-c9eaeb08c079 · outbound

This paper cites LLM-Based Human-Agent Collaboration and Interaction Systems: A Survey.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models LLM-Based Human-Agent Collaboration and Interaction Systems: A Survey

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-05-20T12:33:17.032205Z

Source-reported events for the cited work

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

Observation dbe4cdb2-b66a-47b1-b8a4-34e84a9eaba0 · outbound

This paper cites Do NOT think that much for 2+3=? on the overthinking of long reasoning models.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Do NOT think that much for 2+3=? on the overthinking of long reasoning models

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T12:33:27.856902Z

Source-reported events for the cited work

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

Observation da00537a-ee31-4abb-b79f-54632f800873 · outbound

This paper cites Stop when enough: Adaptive early-stopping for chain-of-thought reasoning.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Stop when enough: Adaptive early-stopping for chain-of-thought reasoning

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-20T12:33:16.996286Z

Source-reported events for the cited work

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

Observation 9bfe9c2b-6937-4a7f-9b90-30d656d09fed · outbound

This paper cites LightThinker: Thinking step-by-step compression.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models LightThinker: Thinking step-by-step compression

Reference 19

Resolution: verified exact; doi, observed 2026-05-20T12:33:16.689340Z

Source-reported events for the cited work

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

Observation a88d2cfb-19e6-4235-8cde-fa3eeb5db25f · outbound

This paper cites Training language models to reason efficiently.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Training language models to reason efficiently

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T12:33:17.828199Z

Source-reported events for the cited work

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

Observation a8a705d8-e805-4445-b57c-f331551ec49e · outbound

This paper cites O1-pruner: Length-harmonizing fine-tuning for o1-like reasoning pruning.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models O1-pruner: Length-harmonizing fine-tuning for o1-like reasoning pruning

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T12:33:27.898285Z

Source-reported events for the cited work

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

Observation 486f159f-0bfc-4c35-a9f8-74109a602adc · outbound

This paper cites C3ot: Generating shorter chain-of- thought without compromising effectiveness.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models C3ot: Generating shorter chain-of- thought without compromising effectiveness

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T12:33:27.875755Z

Source-reported events for the cited work

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

Observation d77e1228-e25b-4908-8fb7-a45cf01d9491 · outbound

This paper cites CoT-valve: Length-compressible chain-of-thought tuning.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models CoT-valve: Length-compressible chain-of-thought tuning

Reference 23

Resolution: verified exact; doi, observed 2026-05-20T12:33:16.700258Z

Source-reported events for the cited work

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

Observation 1b8143f7-acd4-4f90-997d-f2bd8332f469 · outbound

This paper cites Kimi k1.5: Scaling Reinforcement Learning with LLMs.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Kimi k1.5: Scaling Reinforcement Learning with LLMs

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-05-20T12:33:17.018304Z

Source-reported events for the cited work

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

Observation 7e4dd015-b1e0-464a-99a7-737babc10646 · outbound

This paper cites Chain of Draft: Thinking Faster by Writing Less.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Chain of Draft: Thinking Faster by Writing Less

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-20T12:33:17.028404Z

Source-reported events for the cited work

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

Observation 6e9739b7-3568-4638-a2c1-8deb9ce3e8ce · outbound

This paper cites Plan and budget: Effective and efficient test-time scaling on reasoning large language models.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Plan and budget: Effective and efficient test-time scaling on reasoning large language models

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T12:33:27.892340Z

Source-reported events for the cited work

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

Observation 7753fe70-dc94-48fd-a8d7-e525192dfe95 · outbound

This paper cites Concise Thoughts: Impact of Output Length on LLM Reasoning and Cost.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Concise Thoughts: Impact of Output Length on LLM Reasoning and Cost

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-07-28T01:22:17.782417Z

Source-reported events for the cited work

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

Observation e5098606-d243-4794-933f-788a12d9c27e · outbound

This paper cites Token-budget-aware LLM reasoning.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Token-budget-aware LLM reasoning

Reference 28

Resolution: verified exact; doi, observed 2026-05-20T12:33:16.686997Z

Source-reported events for the cited work

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

Observation 6ed3abb5-bd72-4f6a-86e6-60dbe330f4ac · outbound

This paper cites Confidence-coverage gating for early exit.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Confidence-coverage gating for early exit

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T12:33:27.901694Z

Source-reported events for the cited work

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

Observation 79e367ad-3a5d-4e45-bacf-e13463bf5604 · outbound

This paper cites an unresolved cited work.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Unresolved cited work

Reference 30

Resolution: unresolved; raw_fallback, observed 2026-05-20T12:33:27.894508Z

Source-reported events for the cited work

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

Observation 3c670f0d-7f40-4029-b63d-8621c6c4d899 · outbound

This paper cites Efficient test-time scaling via self-calibration.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Efficient test-time scaling via self-calibration

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T12:33:27.870795Z

Source-reported events for the cited work

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

Observation bd0621eb-c662-43b0-9b8b-87cc762a2f17 · outbound

This paper cites Early Stopping Chain-of-thoughts in Large Language Models.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Early Stopping Chain-of-thoughts in Large Language Models

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-05-20T12:33:17.024368Z

Source-reported events for the cited work

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

Observation 9184cf53-7c7a-437e-8a8a-e224a00f38e5 · outbound

This paper cites Entropy After </Think> for reasoning model early exiting.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Entropy After </Think> for reasoning model early exiting

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-05-20T12:33:17.015278Z

Source-reported events for the cited work

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

Observation 8bd00ce0-da14-4647-86fb-e058097c6ddf · outbound

This paper cites Dynamic early exit in reasoning models.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Dynamic early exit in reasoning models

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T12:33:27.873449Z

Source-reported events for the cited work

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

Observation 1fca60b3-b7cd-45a2-abb1-e1b087388db5 · outbound

This paper cites Reasoning without self-doubt: More efficient chain-of-thought through certainty probing.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Reasoning without self-doubt: More efficient chain-of-thought through certainty probing

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T12:33:27.890864Z

Source-reported events for the cited work

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

Observation d90f52dd-63f9-4c67-9ea3-fd764e9bfa94 · outbound

This paper cites Efficient reasoning for large reasoning language models via certainty-guided reflection suppression.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Efficient reasoning for large reasoning language models via certainty-guided reflection suppression

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T12:33:27.864035Z

Source-reported events for the cited work

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

Observation f1212aeb-a28e-4a4e-922a-3a95f43e0aac · outbound

This paper cites Answer convergence as a signal for early stopping in reasoning.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Answer convergence as a signal for early stopping in reasoning

Reference 37

Resolution: verified exact; doi, observed 2026-05-20T12:33:16.702720Z

Source-reported events for the cited work

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

Observation 1ce961b1-1d23-4459-809e-cdb63439596e · outbound

This paper cites Semantic uncertainty: Linguistic invariances for uncertainty estimation in natural language generation.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Semantic uncertainty: Linguistic invariances for uncertainty estimation in natural language generation

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T12:33:27.865805Z

Source-reported events for the cited work

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

Observation 72b3a4cf-8cb0-415a-b98c-c8554e7a1f64 · outbound

This paper cites Detecting hallucinations in large language models using semantic entropy.Nature, 630(8017):625–630.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Detecting hallucinations in large language models using semantic entropy.Nature, 630(8017):625–630

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T12:33:27.870968Z

Source-reported events for the cited work

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

Observation 6057ad64-80bc-480c-8861-3164a5b59628 · outbound

This paper cites Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models

Reference 40

Resolution: verified exact; local_arxiv, observed 2026-05-20T12:33:16.984076Z

Source-reported events for the cited work

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

Observation b7bcc9e4-cb90-437b-8969-36f2f83ebb58 · outbound

This paper cites Representation Learning with Contrastive Predictive Coding.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Representation Learning with Contrastive Predictive Coding

Reference 41

Resolution: verified exact; local_arxiv, observed 2026-05-20T12:33:17.021005Z

Source-reported events for the cited work

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

Observation bd16fb90-57a0-4226-a6c9-f63799421520 · outbound

This paper cites Bie, T., Cao, M., Chen, K., Du, L., Gong, M., Gong, Z., Gu, Y ., Hu, J., Huang, Z., Lan, Z., et al.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Bie, T., Cao, M., Chen, K., Du, L., Gong, M., Gong, Z., Gu, Y ., Hu, J., Huang, Z., Lan, Z., et al

Reference 42

Resolution: metadata mismatch; arxiv_id, observed 2026-05-20T12:33:16.993286Z

Source-reported events for the cited work

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

Observation 60edd21f-6d62-46de-bc60-f962745cbc67 · outbound

This paper cites Measuring mathematical problem solving with the MATH dataset.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Measuring mathematical problem solving with the MATH dataset

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T12:33:27.897841Z

Source-reported events for the cited work

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

Observation da0abe8a-ba31-42f1-b20a-a54ac34e86ce · outbound

This paper cites American invitational mathematics examination (aime) 2024.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models American invitational mathematics examination (aime) 2024

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T12:33:17.833860Z

Source-reported events for the cited work

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

Observation 90467c7e-92a1-44aa-8d35-c346531d39c8 · outbound

This paper cites American invitational mathematics examination (aime) 2025.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models American invitational mathematics examination (aime) 2025

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T12:33:17.816421Z

Source-reported events for the cited work

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

Observation 396c0209-1f19-4b9e-9230-c2d551e68e90 · outbound

This paper cites OlympiadBench: A challenging benchmark for promoting AGI with olympiad-level bilin- gual multimodal scientific problems.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models OlympiadBench: A challenging benchmark for promoting AGI with olympiad-level bilin- gual multimodal scientific problems

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T12:33:17.818568Z

Source-reported events for the cited work

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

Observation 85ebca1f-4bfa-4368-988f-68d417a42d39 · outbound

This paper cites O lympiad B ench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models O lympiad B ench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems

Reference 47

Resolution: metadata mismatch; doi, observed 2026-05-20T12:33:16.692034Z

Source-reported events for the cited work

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

Observation 844b9a8b-43f5-4bcc-911d-1933dd1f5ba7 · outbound

This paper cites an unresolved cited work.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Unresolved cited work

Reference 48

Resolution: unresolved; raw_fallback, observed 2026-05-20T12:33:17.805007Z

Source-reported events for the cited work

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

Observation 5a72d29a-8da5-46bc-a3f7-668923901620 · outbound

This paper cites Stop overthinking: A survey on efficient reasoning for large language models.Transactions on Machine Learning Re- search.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Stop overthinking: A survey on efficient reasoning for large language models.Transactions on Machine Learning Re- search

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T12:33:17.824419Z

Source-reported events for the cited work

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

Observation 43a89133-13cf-4078-b773-10a1e58c1ec9 · outbound

This paper cites Between Underthinking and Overthinking: An Empirical Study of Reasoning Length and correctness in LLMs.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Between Underthinking and Overthinking: An Empirical Study of Reasoning Length and correctness in LLMs

Reference 50

Resolution: verified exact; arxiv_id, observed 2026-05-20T12:33:17.002307Z

Source-reported events for the cited work

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

Observation 6825245e-1d7b-41c6-b133-0786581a77e7 · outbound

This paper cites Does thinking more always help? mirage of test-time scaling in reasoning models.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Does thinking more always help? mirage of test-time scaling in reasoning models

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T12:33:27.896466Z

Source-reported events for the cited work

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

Observation d0696d23-2805-48d4-af21-d3e952e67d28 · outbound

This paper cites When more is less: Understanding chain-of-thought length in LLMs.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models When more is less: Understanding chain-of-thought length in LLMs

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T12:33:17.796140Z

Source-reported events for the cited work

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

Observation 61f5872a-a039-4cb9-b6c9-a508fe84a43a · outbound

This paper cites The evolution of thought: Tracking llm overthinking via reasoning dynamics analysis.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models The evolution of thought: Tracking llm overthinking via reasoning dynamics analysis

Reference 53

Resolution: verified exact; arxiv_id, observed 2026-05-20T12:33:17.048461Z

Source-reported events for the cited work

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

Observation 2af223ce-6d62-4ff5-b100-cfa8ce773695 · outbound

This paper cites L1: Controlling how long a reasoning model thinks with reinforcement learning.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models L1: Controlling how long a reasoning model thinks with reinforcement learning

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T12:33:17.800192Z

Source-reported events for the cited work

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

Observation d285b119-9d9d-480c-af82-4733bab524bb · outbound

This paper cites Thinkprune: Pruning long chain-of-thought of LLMs via reinforcement learning.Transactions on Machine Learning Research.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Thinkprune: Pruning long chain-of-thought of LLMs via reinforcement learning.Transactions on Machine Learning Research

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T12:33:27.859789Z

Source-reported events for the cited work

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

Observation 2a92d67b-1049-43ff-bdf7-bf4d13108e97 · outbound

This paper cites S-GRPO: Early exit via reinforcement learning in reasoning models.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models S-GRPO: Early exit via reinforcement learning in reasoning models

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T12:33:17.807685Z

Source-reported events for the cited work

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

Observation 4ac7ec8d-5ef9-4197-8fb8-705ba032b1a4 · outbound

This paper cites Making slow thinking faster: Compressing LLM chain-of-thought via step entropy.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Making slow thinking faster: Compressing LLM chain-of-thought via step entropy

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T12:33:17.814287Z

Source-reported events for the cited work

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

Observation d78a2358-4e04-477c-8af3-1a64d7199c53 · outbound

This paper cites Training large language models to reason in a continuous latent space.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Training large language models to reason in a continuous latent space

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T12:33:17.798258Z

Source-reported events for the cited work

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

Observation 71665c58-d7ef-472a-ad19-4525a43411ac · outbound

This paper cites Semcot: Accelerating chain-of-thought reasoning through semantically-aligned implicit tokens.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Semcot: Accelerating chain-of-thought reasoning through semantically-aligned implicit tokens

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T12:33:17.790618Z

Source-reported events for the cited work

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

Observation d9b476c9-891f-4fde-9b3c-210ff1638fc0 · outbound

This paper cites LIMO: Less is more for reasoning.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models LIMO: Less is more for reasoning

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T12:33:17.794215Z

Source-reported events for the cited work

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

Observation 4904d132-05f2-4637-89f2-17414d56ef49 · outbound

This paper cites DAPO: An open-source LLM reinforcement learning system at scale.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models DAPO: An open-source LLM reinforcement learning system at scale

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T12:33:17.788741Z

Source-reported events for the cited work

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

Observation 1ff91689-615e-4c83-95a3-0a87bae5e47f · outbound

This paper cites Lee, Wen Sun, Wenhao Zhan, and Xuezhou Zhang.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Lee, Wen Sun, Wenhao Zhan, and Xuezhou Zhang

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T12:33:17.830001Z

Source-reported events for the cited work

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

Observation 51d2725c-10f5-4aed-b7b1-1bc5302f1e1b · outbound

This paper cites 10852426.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models 10852426

Reference 63

Resolution: metadata mismatch; arxiv_id, observed 2026-05-20T12:33:16.697580Z

Source-reported events for the cited work

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

Observation 32bbcca8-4015-4e84-8c98-f36fe12a5891 · outbound

This paper cites PREMISE: Scalable and strategic prompt optimization for efficient mathematical reasoning in large reasoning models.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models PREMISE: Scalable and strategic prompt optimization for efficient mathematical reasoning in large reasoning models

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T12:33:17.792443Z

Source-reported events for the cited work

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

Observation 43d1fb2a-f65d-401c-9989-a18a2beeafa2 · outbound

This paper cites Just ask for calibration: Strategies for eliciting calibrated confidence scores from language models fine-tuned with human feedback.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Just ask for calibration: Strategies for eliciting calibrated confidence scores from language models fine-tuned with human feedback

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T12:33:17.786778Z

Source-reported events for the cited work

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

Observation cf8816c2-af0d-4053-9233-4433f1f7744c · outbound

This paper cites Mind the confidence gap: Overconfidence, calibration, and distractor effects in large language models.Transactions on Machine Learning Research.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Mind the confidence gap: Overconfidence, calibration, and distractor effects in large language models.Transactions on Machine Learning Research

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T12:33:17.782927Z

Source-reported events for the cited work

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

Observation 78017532-213a-4bb2-b680-cc153bfc3489 · outbound

This paper cites Parameterized Inapproximability Hypothesis under Exponential Time Hypothesis , booktitle =.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Parameterized Inapproximability Hypothesis under Exponential Time Hypothesis , booktitle =

Reference 67

Resolution: metadata mismatch; arxiv_id, observed 2026-05-20T12:33:16.684479Z

Source-reported events for the cited work

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

Observation e7506367-7c65-4db0-a467-aa4e7275a065 · outbound

This paper cites NEAT: Neuron-Based Early Exit for Large Reasoning Models.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models NEAT: Neuron-Based Early Exit for Large Reasoning Models

Reference 68

Resolution: verified exact; local_arxiv, observed 2026-05-20T12:33:16.977949Z

Source-reported events for the cited work

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

Observation c1fe7098-7ab3-4194-934c-8927888f5f1d · outbound

This paper cites Wait, we don’t need to “wait”! removing thinking tokens improves reasoning efficiency.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Wait, we don’t need to “wait”! removing thinking tokens improves reasoning efficiency

Reference 69

Resolution: verified exact; doi, observed 2026-05-20T12:33:16.681528Z

Source-reported events for the cited work

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

Observation 56b267fc-38ce-429e-b8ee-3a545e3d1251 · outbound

This paper cites Lynx: Learning dynamic exits for confidence-controlled reasoning.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Lynx: Learning dynamic exits for confidence-controlled reasoning

Reference 70

Resolution: verified exact; arxiv_id, observed 2026-05-20T12:33:16.987025Z

Source-reported events for the cited work

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

Observation e2e534c7-a89f-4b2a-8971-30f2387fd59c · outbound

This paper cites Rea- soning models know when they’re right: Probing hidden states for self-verification.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Rea- soning models know when they’re right: Probing hidden states for self-verification

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T12:33:17.784830Z

Source-reported events for the cited work

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

Observation a5b68585-812f-4357-874d-856258fcf06f · outbound

This paper cites LoRA: Low-rank adaptation of large language models.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models LoRA: Low-rank adaptation of large language models

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T12:33:17.802697Z

Source-reported events for the cited work

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

Observation 051d6b70-5cdd-4ea5-a563-492bfafe1af2 · outbound

This paper cites Learning transferable visual models from natural language supervision.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Learning transferable visual models from natural language supervision

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T12:33:17.809981Z

Source-reported events for the cited work

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

Observation 156bba10-d3b2-4ffd-a71d-fd25fdde48a7 · outbound

This paper cites Stanford University.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Stanford University

Reference 74

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T12:33:27.899953Z

Source-reported events for the cited work

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

Observation d1bf3c0a-ab36-4350-b425-780c1c9e198d · outbound

This paper cites Reasoning Models Can Be Effective Without Thinking.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Reasoning Models Can Be Effective Without Thinking

Reference 75

Resolution: verified exact; arxiv_id, observed 2026-05-20T12:33:17.005773Z

Source-reported events for the cited work

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

Observation b27a18c4-3b6f-49c1-8852-97f52d4cf972 · outbound

This paper cites From generation to judgment: Opportunities and challenges of LLM-as-a-judge.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models From generation to judgment: Opportunities and challenges of LLM-as-a-judge

Reference 76

Resolution: verified exact; doi, observed 2026-05-20T12:33:16.678638Z

Source-reported events for the cited work

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

Observation e228b976-85d2-4398-a4f5-bf2a57578e04 · outbound

This paper cites Mateval: a multi-agent discussion framework for advancing open-ended text evaluation.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Mateval: a multi-agent discussion framework for advancing open-ended text evaluation

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T12:33:27.862003Z

Source-reported events for the cited work

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

Observation bfbcb44d-9594-4522-8288-ee7a502de15c · outbound

This paper cites Dee: Dual-stage explainable evaluation method for text generation.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Dee: Dual-stage explainable evaluation method for text generation

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T12:33:27.875767Z

Source-reported events for the cited work

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

Observation ba4f81be-45c6-4502-8c5a-59b22958b81e · outbound

This paper cites How to configure good in-context sequence for visual question answering.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models How to configure good in-context sequence for visual question answering

Reference 79

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T12:33:17.812028Z

Source-reported events for the cited work

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

Observation 10abb33c-a315-46e3-a63a-f457ba7f409d · outbound

This paper cites MVI-Bench: A Comprehensive Benchmark for Evaluating Robustness to Misleading Visual Inputs in LVLMs.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models MVI-Bench: A Comprehensive Benchmark for Evaluating Robustness to Misleading Visual Inputs in LVLMs

Reference 80

Resolution: verified exact; local_arxiv, observed 2026-05-20T12:33:17.051422Z

Source-reported events for the cited work

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

Observation e88c8668-2bf4-4efb-a3f3-52fe0eda20a6 · outbound

This paper cites Enhancing multimodal in-context learning for image classification through coreset optimization.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Enhancing multimodal in-context learning for image classification through coreset optimization

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T12:33:17.822357Z

Source-reported events for the cited work

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

Observation 17ccbeb2-65bb-4879-9258-a4c6daa44dff · outbound

This paper cites Livecodebench: Holistic and contamination free evaluation of large language models for code.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Livecodebench: Holistic and contamination free evaluation of large language models for code

Reference 82

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T12:33:17.831953Z

Source-reported events for the cited work

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

Observation 84ed4316-39eb-43b0-b6c3-e7983c546089 · outbound

This paper cites Mathvista: Evaluating mathematical reasoning of foundation models in visual contexts.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Mathvista: Evaluating mathematical reasoning of foundation models in visual contexts

Reference 83

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T12:33:27.877805Z

Source-reported events for the cited work

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

Observation a4762a10-1cac-4f53-8075-ce879194ce0b · outbound

This paper cites Measuring multimodal mathematical reasoning with math-vision dataset.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Measuring multimodal mathematical reasoning with math-vision dataset

Reference 84

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T12:33:27.868732Z

Source-reported events for the cited work

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

Observation 1b472278-eda8-43c9-b341-b93ed9d2a117 · outbound

This paper cites Direct preference optimization: Your language model is secretly a reward model.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Direct preference optimization: Your language model is secretly a reward model

Reference 85

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T12:33:27.886122Z

Source-reported events for the cited work

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

Observation 04870cef-681f-433b-8a77-fca775b4e53b · outbound

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

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 86

Resolution: verified exact; local_arxiv, observed 2026-05-20T12:33:16.999062Z

Source-reported events for the cited work

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

Observation b14c2fa0-faf1-4716-bf59-9ac6a17c267f · outbound

This paper cites ConCISE: Confidence-guided compression in step-by-step efficient reasoning.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models ConCISE: Confidence-guided compression in step-by-step efficient reasoning

Reference 87

Resolution: verified exact; doi, observed 2026-05-20T12:33:16.694058Z

Source-reported events for the cited work

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

Observation 1508b962-54f6-4afd-a116-115c1446cf17 · outbound

This paper cites Qwq-32b: Embracing the power of reinforcement learning, March 2025.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Qwq-32b: Embracing the power of reinforcement learning, March 2025

Reference 88

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T12:33:27.888618Z

Source-reported events for the cited work

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

Observation b59f61d7-aa28-4ddd-a7e9-695047f0b179 · outbound

This paper cites gpt-oss-120b & gpt-oss-20b Model Card.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models gpt-oss-120b & gpt-oss-20b Model Card

Reference 89

Resolution: verified exact; local_arxiv, observed 2026-05-20T12:33:17.012208Z

Source-reported events for the cited work

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

Observation a8287bb2-380b-4758-8b1b-01f85e6c650e · outbound

This paper cites GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models

Reference 90

Resolution: verified exact; local_arxiv, observed 2026-05-20T12:33:17.044786Z

Source-reported events for the cited work

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

Observation 52e3b473-71f7-460e-bfce-6b7ca586f37b · outbound

This paper cites Kimi K2: Open Agentic Intelligence.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Kimi K2: Open Agentic Intelligence

Reference 91

Resolution: verified exact; local_arxiv, observed 2026-05-20T12:33:16.980838Z

Source-reported events for the cited work

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

Observation 4e4ea757-4e28-46b8-9685-60bbd07f46cb · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Training Verifiers to Solve Math Word Problems

Reference 92

Resolution: verified exact; local_arxiv, observed 2026-05-20T12:33:17.008946Z

Source-reported events for the cited work

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

Observation 93e64bc1-c3d9-4baf-af9b-e672c0ed8352 · outbound

This paper cites Openthoughts: Data recipes for reasoning mod- els.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models Openthoughts: Data recipes for reasoning mod- els

Reference 93

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T12:33:17.826341Z

Source-reported events for the cited work

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

Observation 937fa194-4638-4bd9-b0f1-4f4401e11bdf · outbound

This paper cites w/o RD Gate.

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models w/o RD Gate

Reference 94

Resolution: malformed identifier; raw_fallback, observed 2026-05-20T12:33:17.820506Z

Source-reported events for the cited work

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

Pith citing papers

Observation 6fac1e0e-034b-4181-ad26-e2a66edfbc7a · inbound

When Does Learning to Stop Help? A Cost-Aware Study of Early Exits in Reasoning Models cites this paper.

When Does Learning to Stop Help? A Cost-Aware Study of Early Exits in Reasoning Models Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-12T10:30:01.871842Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7d57549-a43c-4875-8d53-26e4a3dc9082 · inbound

TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning cites this paper.

TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-07-13T05:38:27.357469Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8bd44b6a-a62a-4be7-bf4b-2bf8d207ca47 · inbound

TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning cites this paper.

TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-02T07:51:14.115517Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.