Paper Citation Record · LEDGER

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision

As of 12 August 2026, this Paper Citation Record lists 79 of 79 outbound references and 15 inbound Pith citation observations for arXiv:2411.16579.

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

pith.paper-citation-record.v1
2411.16579 v1

Coverage vector

measured 79 of 79 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-12T13:02:57.382411Z

measured 94 of 94 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-12T06:34:41.77262+00:00

measured 15 of 15 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-11T11:37:23.509928Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T05:17:40.141555Z

Reference resolution

79 of 79 outbound references displayed

verified exact0
verified fuzzy26
unresolved52
parse uncertain1
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 9b85b934-7e4d-455c-bea5-dc4b1d428ff2 · outbound

This paper cites an unresolved cited work.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Unresolved cited work

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-12T13:02:57.053027Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94f492fd-d4e8-4322-87d3-31e39ed469e0 · outbound

This paper cites GPT-4 Technical Report.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision GPT-4 Technical Report

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-12T13:02:57.058041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c65238e-4661-4a89-9401-86cad5c54540 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-12T13:02:57.062438Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1426059-7b5e-48ca-a452-7dc41a796e9f · outbound

This paper cites Mistral 7B.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Mistral 7B

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-12T13:02:57.066763Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93f973da-c684-4eca-8a3f-341b780182af · outbound

This paper cites The Llama 3 Herd of Models.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision The Llama 3 Herd of Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-12T13:02:57.071218Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f03ad74-ca13-4858-ae7d-49e78ade05a0 · outbound

This paper cites Chi, Quoc V.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Chi, Quoc V

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-12T13:02:57.075651Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a1a82af-11c1-43f4-bf9a-5d7fbce0bbcb · outbound

This paper cites Self-polish: Enhance reasoning in large language models via problem refinement.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Self-polish: Enhance reasoning in large language models via problem refinement

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-12T13:02:57.079955Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed50e2f4-042d-4662-b195-78c4e6c8d05a · outbound

This paper cites Reinforced Self-Training (ReST) for Language Modeling.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Reinforced Self-Training (ReST) for Language Modeling

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-12T13:02:57.083939Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 130fbaa5-bfa7-4d57-ae40-7764142d84e2 · outbound

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

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Tree of thoughts: Deliberate problem solving with large language models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-12T13:02:57.088052Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f76c35f2-4c68-4bb2-bab0-c34d8c36d669 · outbound

This paper cites WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-12T13:02:57.091954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22af9057-d6a2-4667-86a3-4fa58103ef42 · outbound

This paper cites Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-12T13:02:57.095809Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a45ee4b7-2e0e-44f3-92d2-e5f618b89784 · outbound

This paper cites Narasimhan, and Yuan Cao.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Narasimhan, and Yuan Cao

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-12T13:02:57.099726Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c8e6dd0-4841-4059-8203-229da2653d4a · outbound

This paper cites Learning to reason with llms, 9 2024.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Learning to reason with llms, 9 2024

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:02:58.224784Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation c16b122c-e1ec-4ca1-9f9f-7967a0689750 · outbound

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

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Reflexion: language agents with verbal reinforcement learning

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:02:58.214036Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 9bc88d17-6261-4d2f-a612-74d0399dda58 · outbound

This paper cites Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-12T13:02:57.114944Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b490c3a-3440-4798-b6a8-a5a1a2c82b60 · outbound

This paper cites Recursive Introspection: Teaching Language Model Agents How to Self-Improve.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Recursive Introspection: Teaching Language Model Agents How to Self-Improve

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-12T13:02:57.118753Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bdcb9261-86a0-42a7-bb2a-09f121e47e72 · outbound

This paper cites Training Language Models to Self-Correct via Reinforcement Learning.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Training Language Models to Self-Correct via Reinforcement Learning

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-12T13:02:57.122914Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 012ce922-4711-4dd4-9118-70730d848644 · outbound

This paper cites Generating sequences by learning to self-correct.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Generating sequences by learning to self-correct

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:02:58.202601Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 2144d6c3-d0b3-490a-b89c-ae48bf6d13f3 · outbound

This paper cites Pride and prejudice: LLM amplifies self-bias in self-refinement.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Pride and prejudice: LLM amplifies self-bias in self-refinement

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:02:58.191472Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation bb67ad25-58e2-4fcc-b837-62227c7a50e2 · outbound

This paper cites Selfee: Iterative self-revising llm empowered by self-feedback generation.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Selfee: Iterative self-revising llm empowered by self-feedback generation

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:02:58.180246Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation a6521300-0f7c-4653-b495-f14d13535223 · outbound

This paper cites Language models can solve computer tasks.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Language models can solve computer tasks

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:02:58.168099Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation a69af469-747b-41aa-b80d-523013afd16e · outbound

This paper cites Self-critiquing models for assisting human evaluators.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Self-critiquing models for assisting human evaluators

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-12T13:02:57.142310Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d33bfbb6-a0c1-4f9b-bef9-9b41eebfd00f · outbound

This paper cites Self-refine: Iterative refinement with self-feedback.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Self-refine: Iterative refinement with self-feedback

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:02:58.156112Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 64ae9e86-e13a-4b03-94fb-fd3203b108a9 · outbound

This paper cites Large language models cannot self-correct reasoning yet.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Large language models cannot self-correct reasoning yet

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:02:58.143170Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 7fba3881-f542-4fa1-b9e4-33b0aeca8e00 · outbound

This paper cites RL4F: generating natural language feedback with reinforcement learning for repairing model outputs.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision RL4F: generating natural language feedback with reinforcement learning for repairing model outputs

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:02:58.131161Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation af4c5e23-97c0-49c0-a684-1f0500b8f7f9 · outbound

This paper cites N., Zeyuan Chen, Jianguo Zhang, Devansh Arpit, Ran Xu, Phil Mui, Huan Wang, Caiming Xiong, and Silvio Savarese.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision N., Zeyuan Chen, Jianguo Zhang, Devansh Arpit, Ran Xu, Phil Mui, Huan Wang, Caiming Xiong, and Silvio Savarese

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:02:58.117592Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation e194bb0c-ecc1-498a-96c0-b752fb219996 · outbound

This paper cites Glore: When, where, and how to improve LLM reasoning via global and local refinements.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Glore: When, where, and how to improve LLM reasoning via global and local refinements

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:02:58.104913Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation fd04a305-fb82-4246-8db9-5efdef3f83b8 · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Constitutional AI: Harmlessness from AI Feedback

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-12T13:02:57.164895Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 14a6d641-dcb1-4ee2-95f4-e69ed53ebdf8 · outbound

This paper cites Measuring Progress on Scalable Oversight for Large Language Models.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Measuring Progress on Scalable Oversight for Large Language Models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-12T13:02:57.168900Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af6fb549-3f18-4913-8f48-b96a6aef19a9 · outbound

This paper cites Math-shepherd: Verify and reinforce llms step-by-step without human annotations.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Math-shepherd: Verify and reinforce llms step-by-step without human annotations

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:02:58.092948Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation ec8316a1-d2a4-4c13-a741-f4d2efe5a023 · outbound

This paper cites Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-12T13:02:57.176993Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d27df5c-156d-4edb-998c-ccdb77c6dcd2 · outbound

This paper cites Large Language Monkeys: Scaling Inference Compute with Repeated Sampling.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Large Language Monkeys: Scaling Inference Compute with Repeated Sampling

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-12T13:02:57.181044Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67fb4773-3482-437c-af28-a94b36d1c356 · outbound

This paper cites Smaller, Weaker, Yet Better: Training LLM Reasoners via Compute-Optimal Sampling.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Smaller, Weaker, Yet Better: Training LLM Reasoners via Compute-Optimal Sampling

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-12T13:02:57.185103Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea4f1dc3-f386-498a-9adc-e96f14b8b585 · outbound

This paper cites Mitigating Tail Narrowing in LLM Self-Improvement via Socratic-Guided Sampling.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Mitigating Tail Narrowing in LLM Self-Improvement via Socratic-Guided Sampling

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-12T13:02:57.189007Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82f5d69d-a297-47b4-b333-11544a25e142 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Training Verifiers to Solve Math Word Problems

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-12T13:02:57.193025Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48c564a4-6a9f-4e63-bfad-2d72e49e58c7 · outbound

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

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Measuring mathematical problem solving with the MATH dataset

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-12T13:02:57.197231Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7242bde7-3079-44ff-961a-59baeece291b · outbound

This paper cites Measuring Faithfulness in Chain-of-Thought Reasoning.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Measuring Faithfulness in Chain-of-Thought Reasoning

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-12T13:02:57.201073Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef045c5b-3a65-46bf-9aea-a40dc452f808 · outbound

This paper cites Evaluating mathematical reasoning of large language models: A focus on error identification and correction.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Evaluating mathematical reasoning of large language models: A focus on error identification and correction

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:02:58.064008Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 88d756a0-ec1d-41f9-bc42-cadb0297302a · outbound

This paper cites ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-12T13:02:57.208906Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87d0a53f-000a-47de-8884-68101bd7bffe · outbound

This paper cites DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-12T13:02:57.213083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6ab7f3d-ef8a-4b33-9cfc-f7418fbd81d2 · outbound

This paper cites Le, Ed H.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Le, Ed H

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:02:58.048170Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation bb421daf-65bf-452b-8d93-5fd5540e663f · outbound

This paper cites Large language models can self-improve.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Large language models can self-improve

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:02:58.033956Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation a140117e-8ccd-4d50-820a-96af5bac56c3 · outbound

This paper cites ReST meets ReAct: Self-Improvement for Multi-Step Reasoning LLM Agent.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision ReST meets ReAct: Self-Improvement for Multi-Step Reasoning LLM Agent

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-12T13:02:57.225484Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bf0d1da-e5ec-4971-8d03-d054db731fe6 · outbound

This paper cites Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-12T13:02:57.230261Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e969d2a-a5d1-4d54-97bf-24e39de11f97 · outbound

This paper cites Re-rest: Reflection-reinforced self-training for language agents.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Re-rest: Reflection-reinforced self-training for language agents

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:02:58.021031Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation dbc49a4f-f48a-4f22-9da2-f6a508890715 · outbound

This paper cites an unresolved cited work.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Unresolved cited work

Reference 46

Resolution: unresolved; raw_fallback, observed 2026-08-12T13:02:58.009509Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 1691a1df-8419-4c99-bfe4-080641d630aa · outbound

This paper cites AgentGym: Evolving Large Language Model-based Agents across Diverse Environments.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision AgentGym: Evolving Large Language Model-based Agents across Diverse Environments

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-12T13:02:57.241810Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34f8f316-6282-4d03-bfdf-25d850dbdcff · outbound

This paper cites Progress or Regress? Self-Improvement Reversal in Post-training.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Progress or Regress? Self-Improvement Reversal in Post-training

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-12T13:02:57.245849Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf24d1b9-42ea-44e1-8556-595620fcb0b4 · outbound

This paper cites Qwen2.5: A party of foundation models, September 2024.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Qwen2.5: A party of foundation models, September 2024

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-12T13:02:57.252023Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b244a35-1f88-43a7-bcf1-afa4f169b5c6 · outbound

This paper cites Selfcheck: Using llms to zero-shot check their own step-by-step reasoning.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Selfcheck: Using llms to zero-shot check their own step-by-step reasoning

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-12T13:02:57.256215Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5fe4b374-f31b-4527-a686-3133d1c68f29 · outbound

This paper cites an unresolved cited work.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Unresolved cited work

Reference 51

Resolution: unresolved; raw_fallback, observed 2026-08-12T13:02:57.982839Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 1ae59c0b-ab6c-4aac-b878-98f5b50aadb7 · outbound

This paper cites Mondal, and Jyoti Prakash Sahoo.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Mondal, and Jyoti Prakash Sahoo

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:02:57.970806Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 24fb9d47-5b30-42ca-aec4-858dd01ad312 · outbound

This paper cites Smith, Daniel Khashabi, and Hannaneh Hajishirzi.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Smith, Daniel Khashabi, and Hannaneh Hajishirzi

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:02:57.958655Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 599203ec-1368-4c74-ac60-8e2e8612a6ba · outbound

This paper cites Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-12T13:02:57.278896Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca763e23-2533-4af3-843c-50c52e14451c · outbound

This paper cites The Curse of Recursion: Training on Generated Data Makes Models Forget.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision The Curse of Recursion: Training on Generated Data Makes Models Forget

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-12T13:02:57.284688Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39f744c1-b888-4e41-8a83-2dc4df53fa70 · outbound

This paper cites Baraniuk.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Baraniuk

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:02:57.946968Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 07f524a7-62e5-4f5e-adc4-807c59ae17bc · outbound

This paper cites Let’s verify step by step.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Let’s verify step by step

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-12T13:02:57.293636Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb958596-548b-4030-a356-a856f6a6f555 · outbound

This paper cites Improving discriminative capability of reward models in RLHF using contrastive learning.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Improving discriminative capability of reward models in RLHF using contrastive learning

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:02:57.927529Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 91ae101e-4aa1-4e22-b5dc-fa35983840bc · outbound

This paper cites Improving Code Generation by Training with Natural Language Feedback.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Improving Code Generation by Training with Natural Language Feedback

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-12T13:02:57.303363Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 954f32ce-ea5b-4f23-9461-f87c5059f4b7 · outbound

This paper cites REFINER: reasoning feedback on intermediate representations.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision REFINER: reasoning feedback on intermediate representations

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:02:57.915523Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 92a539d3-a388-4bf8-9cce-fcb2a9ef830e · outbound

This paper cites Chain-of-verification reduces hallucination in large language models.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Chain-of-verification reduces hallucination in large language models

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-12T13:02:57.311887Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1948d6d-46a3-47b5-b3e5-08d72aebc32f · outbound

This paper cites Shepherd: A Critic for Language Model Generation.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Shepherd: A Critic for Language Model Generation

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-12T13:02:57.315505Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 795dfabc-4141-4ee9-9b55-b4a768b7ea63 · outbound

This paper cites LLM Critics Help Catch Bugs in Mathematics: Towards a Better Mathematical Verifier with Natural Language Feedback.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision LLM Critics Help Catch Bugs in Mathematics: Towards a Better Mathematical Verifier with Natural Language Feedback

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-12T13:02:57.319981Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 774731a3-8338-41ce-b126-8f6c637b6933 · outbound

This paper cites Solving challenging math word problems using GPT-4 code interpreter with code-based self-verification.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Solving challenging math word problems using GPT-4 code interpreter with code-based self-verification

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-12T13:02:57.324170Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b434e77e-61b7-4d83-b395-88e19cc9580f · outbound

This paper cites Generative Verifiers: Reward Modeling as Next-Token Prediction.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Generative Verifiers: Reward Modeling as Next-Token Prediction

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-12T13:02:57.329005Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 422a3b00-9233-4aac-8e9b-fab3048c7751 · outbound

This paper cites Critique-out-Loud Reward Models.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Critique-out-Loud Reward Models

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-12T13:02:57.332836Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8ad3372-b218-494d-b01e-37cc0c3a104c · outbound

This paper cites Critic-cot: Boosting the reasoning abilities of large language model via chain-of-thoughts critic, 2024.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Critic-cot: Boosting the reasoning abilities of large language model via chain-of-thoughts critic, 2024

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:02:57.891035Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 5fac2cbc-9969-4738-8c1b-220248c459f6 · outbound

This paper cites Du, and Beibin Li.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Du, and Beibin Li

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:02:57.879844Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation f2361f55-f8e0-445e-9b32-f684091edaec · outbound

This paper cites Ovm, outcome-supervised value models for planning in mathematical reasoning.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Ovm, outcome-supervised value models for planning in mathematical reasoning

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:02:57.867564Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation d0182e75-c839-4538-8707-a8e4e9b60d2e · outbound

This paper cites Reasoning with language model is planning with world model.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Reasoning with language model is planning with world model

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:02:57.856336Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 20e0f25b-9982-411c-b1cc-8652aed6fd47 · outbound

This paper cites AlphaMath Almost Zero: Process Supervision without Process.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision AlphaMath Almost Zero: Process Supervision without Process

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-12T13:02:57.353698Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a67b251-f41c-42ba-a47d-927695d4d923 · outbound

This paper cites LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-12T13:02:57.358278Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67e3159a-8a46-4147-8b9b-7bb9fed0ef89 · outbound

This paper cites Measuring massive multitask language understanding.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Measuring massive multitask language understanding

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-12T13:02:57.362740Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57bb5f76-3bdb-46ef-bdca-8e8ef5a1beee · outbound

This paper cites GPQA: A Graduate-Level Google-Proof Q&A Benchmark.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision GPQA: A Graduate-Level Google-Proof Q&A Benchmark

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-12T13:02:57.366306Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef4192da-68bc-4261-84f7-0de63c9cbb10 · outbound

This paper cites Evaluating Large Language Models Trained on Code.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Evaluating Large Language Models Trained on Code

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-12T13:02:57.370629Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93d8110f-bc3e-4cf2-b6df-4d47b64ebe83 · outbound

This paper cites Program Synthesis with Large Language Models.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Program Synthesis with Large Language Models

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-12T13:02:57.374858Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c771502a-0222-42a2-b935-c432d9d54c64 · outbound

This paper cites Webshop: Towards scalable real-world web interaction with grounded language agents.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Webshop: Towards scalable real-world web interaction with grounded language agents

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:02:57.837662Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation f26ec808-d6a6-4b73-a46f-b56e2d85372a · outbound

This paper cites The Rise and Potential of Large Language Model Based Agents: A Survey.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision The Rise and Potential of Large Language Model Based Agents: A Survey

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-12T13:02:57.382411Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04e7144a-3a3c-4394-bdd5-e78bc2a7f891 · outbound

This paper cites an unresolved cited work.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision Unresolved cited work

Reference 2023

Resolution: parse uncertain; no resolver link, observed 2026-08-12T13:02:57.103229Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation c5b677c2-a98c-4230-8e5b-7383d98fe7b3 · inbound

Critical-Questions-of-Thought: Steering LLM reasoning with Argumentative Querying cites this paper.

Critical-Questions-of-Thought: Steering LLM reasoning with Argumentative Querying Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-11T11:37:23.509928Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c206319f-92cb-444b-9adf-3a15c3694d30 · inbound

Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training cites this paper.

Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-10T18:22:02.691028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2ac63d0-277d-4136-855b-3533293a6cef · inbound

Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search cites this paper.

Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-09T11:57:48.778636Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b592302-f65d-4675-a45c-b0b19ad6b29d · inbound

TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling cites this paper.

TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T15:00:38.405708Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e23b3e40-b19e-44cb-9332-01a0262f1503 · inbound

Stepwise Reasoning Checkpoint Analysis: A Test Time Scaling Method to Enhance LLMs' Reasoning cites this paper.

Stepwise Reasoning Checkpoint Analysis: A Test Time Scaling Method to Enhance LLMs' Reasoning Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T14:45:19.417118Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f10f4ed-9f2c-40c9-bd52-d9d96a11b99d · inbound

Large Language Models for Planning: A Comprehensive and Systematic Survey cites this paper.

Large Language Models for Planning: A Comprehensive and Systematic Survey Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision

Reference 289

Resolution: unresolved; no resolver link, observed 2026-08-07T14:12:10.512934Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e88dd56-b72d-4bbb-a544-7ee3bc701ca1 · inbound

Step-Wise Formal Verification for LLM-Based Mathematical Problem Solving cites this paper.

Step-Wise Formal Verification for LLM-Based Mathematical Problem Solving Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T13:48:59.112150Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9615e3cf-cb0d-45df-8835-0d74c2c1830c · inbound

Making VLMs More Robot-Friendly: Self-Critical Distillation of Low-Level Procedural Reasoning cites this paper.

Making VLMs More Robot-Friendly: Self-Critical Distillation of Low-Level Procedural Reasoning Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-06T18:30:47.251015Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83c9f6db-1dba-49fa-94ed-9c3d312980ed · inbound

R4ec: A Reasoning, Reflection, and Refinement Framework for Recommendation Systems cites this paper.

R4ec: A Reasoning, Reflection, and Refinement Framework for Recommendation Systems Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-06T14:58:28.118937Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7aacda37-b046-471e-be59-73e724a8bec2 · inbound

A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence cites this paper.

A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision

Reference 171

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T22:23:14.944730Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 3396766a-ad2a-4185-b315-f00feb8a3e76 · inbound

Learning from Natural Language Feedback for Personalized Question Answering cites this paper.

Learning from Natural Language Feedback for Personalized Question Answering Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision

Reference 37

Resolution: verified exact; arxiv_id, observed 2026-05-18T22:56:53.045875Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 6eafc153-32dd-404d-9036-6b9ae1198fbe · inbound

XRPO: Pushing the limits of GRPO with Targeted Exploration and Exploitation cites this paper.

XRPO: Pushing the limits of GRPO with Targeted Exploration and Exploitation Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision

Reference 1992

Resolution: unresolved; no resolver link, observed 2026-08-04T11:11:12.780313Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5360fa2-2d32-4f45-aa09-c34df55eb6aa · inbound

No More Stale Feedback: Co-Evolving Critics for Open-World Agent Learning cites this paper.

No More Stale Feedback: Co-Evolving Critics for Open-World Agent Learning Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision

Reference 19

Resolution: metadata mismatch; arxiv_id, observed 2026-05-16T16:03:04.330035Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 6207f2ce-2e63-428e-8042-23e0caf6e0ae · inbound

STRIDE: Learnable Stepwise Language Feedback for LLM Reasoning cites this paper.

STRIDE: Learnable Stepwise Language Feedback for LLM Reasoning Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-20T20:49:00.673885Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 39681fe5-9020-4b3e-8b23-27317878f03d · inbound

A History-Aware Visually Grounded Critic for Computer Use Agents cites this paper.

A History-Aware Visually Grounded Critic for Computer Use Agents Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-07-03T05:17:40.143173Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.