Enhancing LLM Metacognition via Cognitive Pairwise Training | Paper Citation Record

Observation 6e8ddb13-d959-4422-9b56-a948ff9426aa · outbound

This paper cites Kimi K2.5: Visual Agentic Intelligence.

Enhancing LLM Metacognition via Cognitive Pairwise Training Kimi K2.5: Visual Agentic Intelligence

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-06-28T19:02:33.919403Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 3e27f3d8-cc51-4dcd-9db2-313b076fff82 · outbound

This paper cites Qwen3 Technical Report.

Enhancing LLM Metacognition via Cognitive Pairwise Training Qwen3 Technical Report

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-06-28T19:02:33.921975Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f826adc3-6a16-47a0-820c-41ed6a9e9b75 · outbound

This paper cites DeepSeek-V4: Towards highly efficient million-token context intelligence,.

Enhancing LLM Metacognition via Cognitive Pairwise Training DeepSeek-V4: Towards highly efficient million-token context intelligence,

Reference 3

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2664db67-8658-47b0-9f2c-8be158890c6a · outbound

This paper cites OpenClaw-RL: Train Any Agent Simply by Talking.

Enhancing LLM Metacognition via Cognitive Pairwise Training OpenClaw-RL: Train Any Agent Simply by Talking

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-06-28T19:02:33.914341Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 01c10909-202d-4780-a831-d277e9189004 · outbound

This paper cites Magpie: Alignment data synthesis from scratch by prompting aligned LLMs with nothing,.

Enhancing LLM Metacognition via Cognitive Pairwise Training Magpie: Alignment data synthesis from scratch by prompting aligned LLMs with nothing,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dda4e049-f471-4511-a460-3987c6c3876d · outbound

This paper cites Tongyi DeepResearch Technical Report.

Enhancing LLM Metacognition via Cognitive Pairwise Training Tongyi DeepResearch Technical Report

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-06-28T19:02:33.916799Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 0b73d65d-9913-4209-86cf-830410a43f4f · outbound

This paper cites Language models are few-shot learners,.

Enhancing LLM Metacognition via Cognitive Pairwise Training Language models are few-shot learners,

Reference 7

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b034ec21-6d64-4e82-a233-b050464ceda3 · outbound

This paper cites Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agents.

Enhancing LLM Metacognition via Cognitive Pairwise Training Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agents

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-06-28T19:02:33.924827Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ec3f4121-2ca0-48b7-b902-31ee327523cb · outbound

This paper cites Cbr-rag: case-based reasoning for retrieval augmented generation in llms for legal question answering,.

Enhancing LLM Metacognition via Cognitive Pairwise Training Cbr-rag: case-based reasoning for retrieval augmented generation in llms for legal question answering,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1263faa-8c19-466e-8740-322a3025e680 · outbound

This paper cites Improving Retrieval for RAG based Question Answering Models on Financial Documents.

Enhancing LLM Metacognition via Cognitive Pairwise Training Improving Retrieval for RAG based Question Answering Models on Financial Documents

Reference 10

Resolution: metadata mismatch; arxiv_id, observed 2026-06-28T19:02:33.911742Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 5ee71bc8-a2b4-4e17-88cb-69ce72df285f · outbound

This paper cites WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation.

Enhancing LLM Metacognition via Cognitive Pairwise Training WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-06-28T19:02:33.881402Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 536ded1c-c08a-4e55-8639-549244faeaeb · outbound

This paper cites Hallucinations Undermine Trust; Metacognition is a Way Forward.

Enhancing LLM Metacognition via Cognitive Pairwise Training Hallucinations Undermine Trust; Metacognition is a Way Forward

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-06-28T19:02:33.880648Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 48bbdb7d-c90a-475e-b46b-b7eafbf7f55b · outbound

This paper cites Metacognition and cognitive monitoring: A new area of cognitive-developmental inquiry,.

Enhancing LLM Metacognition via Cognitive Pairwise Training Metacognition and cognitive monitoring: A new area of cognitive-developmental inquiry,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b979ac2-2b79-4fb1-8aaa-4e319465e85f · outbound

This paper cites Language Models (Mostly) Know What They Know.

Enhancing LLM Metacognition via Cognitive Pairwise Training Language Models (Mostly) Know What They Know

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-06-28T19:02:33.876321Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ae1f67ed-030e-4eb2-90e2-f674a127993f · outbound

This paper cites Deepseek-r1 incentivizes reasoning in llms through reinforcement learning,.

Enhancing LLM Metacognition via Cognitive Pairwise Training Deepseek-r1 incentivizes reasoning in llms through reinforcement learning,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19f04b23-eba5-4293-a7d0-3b07fc25ec0c · outbound

This paper cites Are Reasoning Models More Prone to Hallucination?.

Enhancing LLM Metacognition via Cognitive Pairwise Training Are Reasoning Models More Prone to Hallucination?

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-06-28T19:02:33.919996Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b45fbbee-7570-484d-9940-b4e60a599413 · outbound

This paper cites Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models.

Enhancing LLM Metacognition via Cognitive Pairwise Training Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-06-28T19:02:33.917472Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 46c1d457-8f31-445a-aa80-e03da166da28 · outbound

This paper cites Haotian Luo, Li Shen, Haiying He, Yibo Wang, Shi- wei Liu, Wei Li, Naiqiang Tan, Xiaochun Cao, and Dacheng Tao.

Enhancing LLM Metacognition via Cognitive Pairwise Training Haotian Luo, Li Shen, Haiying He, Yibo Wang, Shi- wei Liu, Wei Li, Naiqiang Tan, Xiaochun Cao, and Dacheng Tao

Reference 18

Resolution: metadata mismatch; arxiv_id, observed 2026-06-28T19:02:33.930698Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation bc404058-8563-4522-8e45-f5c31132fa01 · outbound

This paper cites The hallucination tax of reinforcement finetuning,.

Enhancing LLM Metacognition via Cognitive Pairwise Training The hallucination tax of reinforcement finetuning,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9164ef4-4993-4756-b43b-715dcb4ba286 · outbound

This paper cites A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions,.

Enhancing LLM Metacognition via Cognitive Pairwise Training A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ea8474f-eead-4af0-8688-406c3a8d4427 · outbound

This paper cites A survey of confidence estimation and calibration in large language models,.

Enhancing LLM Metacognition via Cognitive Pairwise Training A survey of confidence estimation and calibration in large language models,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e54d488d-13ca-4b09-8acb-a52de0d7c7a7 · outbound

This paper cites R-tuning: Instructing large language models to say ‘i don’t know’,.

Enhancing LLM Metacognition via Cognitive Pairwise Training R-tuning: Instructing large language models to say ‘i don’t know’,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bcde1d15-6972-4ab5-9dcc-adcf6d8f9fc7 · outbound

This paper cites Beyond “i don’t know.

Enhancing LLM Metacognition via Cognitive Pairwise Training Beyond “i don’t know

Reference 23

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76586b7a-ba5f-4e02-af6c-ef27f171fc42 · outbound

This paper cites Inference-time scaling for generalist reward modeling.

Enhancing LLM Metacognition via Cognitive Pairwise Training Inference-time scaling for generalist reward modeling

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-06-28T19:02:33.814905Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 7b1533b5-c7d5-4b7c-b113-75ec43816771 · outbound

This paper cites Let’s verify step by step,.

Enhancing LLM Metacognition via Cognitive Pairwise Training Let’s verify step by step,

Reference 25

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6bdf2e05-4eb1-4d78-b2cd-0c719b5ca6bc · outbound

This paper cites Agent Learning via Early Experience.

Enhancing LLM Metacognition via Cognitive Pairwise Training Agent Learning via Early Experience

Reference 26

Resolution: metadata mismatch; local_arxiv, observed 2026-06-28T19:02:33.901234Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 69f4d5fa-622e-4ea7-af9d-c4a5e2a7a8fb · outbound

This paper cites General agents need world models,.

Enhancing LLM Metacognition via Cognitive Pairwise Training General agents need world models,

Reference 27

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0148317a-91c0-4eb4-af55-577250628e3e · outbound

This paper cites Model Spec Midtraining: Improving How Alignment Training Generalizes.

Enhancing LLM Metacognition via Cognitive Pairwise Training Model Spec Midtraining: Improving How Alignment Training Generalizes

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-06-28T19:02:33.927866Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 3bf6a049-c66c-470b-bb4d-773a5d06abf7 · outbound

This paper cites Training language models to follow instructions with human feedback,.

Enhancing LLM Metacognition via Cognitive Pairwise Training Training language models to follow instructions with human feedback,

Reference 29

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be427412-84bf-4b43-a144-80da635d787e · outbound

This paper cites Judging LLM-as-a-Judge with MT-Bench and chatbot arena,.

Enhancing LLM Metacognition via Cognitive Pairwise Training Judging LLM-as-a-Judge with MT-Bench and chatbot arena,

Reference 30

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22be0e16-e232-4b4e-ad20-8d2fe9c07c9f · outbound

This paper cites Large Language Models are not Fair Evaluators.

Enhancing LLM Metacognition via Cognitive Pairwise Training Large Language Models are not Fair Evaluators

Reference 31

Resolution: verified exact; local_arxiv, observed 2026-06-28T19:02:33.911851Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 96c9eaa7-6613-43ec-8d14-cadead6e7799 · outbound

This paper cites The False Promise of Imitating Proprietary LLMs.

Enhancing LLM Metacognition via Cognitive Pairwise Training The False Promise of Imitating Proprietary LLMs

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-06-28T19:02:33.871338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 98974800-0815-4d80-b88f-fade31ec5c41 · outbound

This paper cites The Llama 3 Herd of Models.

Enhancing LLM Metacognition via Cognitive Pairwise Training The Llama 3 Herd of Models

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-06-28T19:02:33.873974Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d75d3a30-7166-4658-8725-27c38f14f4ce · outbound

This paper cites Olmo 3.

Enhancing LLM Metacognition via Cognitive Pairwise Training Olmo 3

Reference 34

Resolution: verified exact; local_arxiv, observed 2026-06-28T19:02:33.903560Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 1c7dbb91-ded5-459e-b334-c1a6e338d509 · outbound

This paper cites AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions.

Enhancing LLM Metacognition via Cognitive Pairwise Training AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions

Reference 35

Resolution: verified exact; arxiv_id, observed 2026-06-28T19:02:33.904071Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 9a9ffb7a-3497-4017-8609-368dc776c869 · outbound

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

Enhancing LLM Metacognition via Cognitive Pairwise Training Self-refine: Iterative refinement with self-feedback,

Reference 36

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 793a895a-3150-4339-b11d-08e14176726a · outbound

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

Enhancing LLM Metacognition via Cognitive Pairwise Training Reflexion: Language agents with verbal reinforcement learning,

Reference 37

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 297b0023-3a7d-453c-bc1a-5b71026d70f3 · outbound

This paper cites Beyond Binary Rewards: Training LMs to Reason About Their Uncertainty.

Enhancing LLM Metacognition via Cognitive Pairwise Training Beyond Binary Rewards: Training LMs to Reason About Their Uncertainty

Reference 38

Resolution: metadata mismatch; local_arxiv, observed 2026-06-28T19:02:33.868887Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 4009fc6c-eddc-4428-a058-4313f964beae · outbound

This paper cites arXiv preprint arXiv:2503.02623 (2025).

Enhancing LLM Metacognition via Cognitive Pairwise Training arXiv preprint arXiv:2503.02623 (2025)

Reference 39

Resolution: metadata mismatch; arxiv_id, observed 2026-06-28T19:02:33.884024Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f89db0cc-e6cd-423d-8f01-af7e97b9fdad · outbound

This paper cites MASH: Modeling Abstention via Selective Help-Seeking.

Enhancing LLM Metacognition via Cognitive Pairwise Training MASH: Modeling Abstention via Selective Help-Seeking

Reference 40

Resolution: verified exact; local_arxiv, observed 2026-06-28T19:02:33.824556Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 22626431-2395-4ad5-83f5-eeca25ed775e · outbound

This paper cites SelectLLM: Query-aware efficient selection algorithm for large language models,.

Enhancing LLM Metacognition via Cognitive Pairwise Training SelectLLM: Query-aware efficient selection algorithm for large language models,

Reference 41

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7bb3cf00-a191-4d71-8362-43f8533d3dd1 · outbound

This paper cites Know More, Know Clearer: A Meta-Cognitive Framework for Knowledge Augmentation in Large Language Models.

Enhancing LLM Metacognition via Cognitive Pairwise Training Know More, Know Clearer: A Meta-Cognitive Framework for Knowledge Augmentation in Large Language Models

Reference 42

Resolution: metadata mismatch; local_arxiv, observed 2026-06-28T19:02:33.883180Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 99a67573-e027-4352-bcb5-01aeddfabfc4 · outbound

This paper cites SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild.

Enhancing LLM Metacognition via Cognitive Pairwise Training SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild

Reference 43

Resolution: verified exact; local_arxiv, observed 2026-06-28T19:02:33.906505Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 88e877e0-dd6b-4dbf-b637-782b6253c19a · outbound

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

Enhancing LLM Metacognition via Cognitive Pairwise Training DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 44

Resolution: verified exact; local_arxiv, observed 2026-06-28T19:02:33.841748Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d8670fb6-0709-4e4b-87e2-16f1c366d255 · outbound

This paper cites Measuring Mathematical Problem Solving With the MATH Dataset.

Enhancing LLM Metacognition via Cognitive Pairwise Training Measuring Mathematical Problem Solving With the MATH Dataset

Reference 45

Resolution: verified exact; local_arxiv, observed 2026-06-28T19:02:33.889375Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ed3a809b-6e16-4dfe-9c23-b6b936641b66 · outbound

This paper cites OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems.

Enhancing LLM Metacognition via Cognitive Pairwise Training OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems

Reference 46

Resolution: verified exact; local_arxiv, observed 2026-06-28T19:02:33.889808Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation c34744f3-830a-4218-91fc-9156b47103ee · outbound

This paper cites Solving quantitative reasoning problems with language models,.

Enhancing LLM Metacognition via Cognitive Pairwise Training Solving quantitative reasoning problems with language models,

Reference 47

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef3ecce6-8f6c-48e3-8a58-21d2d154cbff · outbound

This paper cites AIMO validation AMC: Problems from AMC 12 2022–2023.

Enhancing LLM Metacognition via Cognitive Pairwise Training AIMO validation AMC: Problems from AMC 12 2022–2023

Reference 48

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5ceee4f-0029-4968-9fd1-85633bfcbb75 · outbound

This paper cites AIMO validation AIME: Problems from AIME 2022–2024.

Enhancing LLM Metacognition via Cognitive Pairwise Training AIMO validation AIME: Problems from AIME 2022–2024

Reference 49

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96b2c637-b915-4de9-9ba4-30cf970d492c · outbound

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

Enhancing LLM Metacognition via Cognitive Pairwise Training Direct preference optimization: Your language model is secretly a reward model,

Reference 50

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2dd81aa2-bd44-4698-ac8e-88695aac5ab3 · outbound

This paper cites Hybridflow: A flexible and efficient rlhf framework,.

Enhancing LLM Metacognition via Cognitive Pairwise Training Hybridflow: A flexible and efficient rlhf framework,

Reference 51

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7c0216d-0df6-49d0-af4a-e7b23f66b916 · outbound

This paper cites Efficient memory management for large language model serving with PagedAttention,.

Enhancing LLM Metacognition via Cognitive Pairwise Training Efficient memory management for large language model serving with PagedAttention,

Reference 52

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8eaa26c5-9c30-425c-b68c-50887251c3cf · outbound

This paper cites DRAGged into Conflicts: Detecting and Addressing Conflicting Sources in Search-Augmented LLMs.

Enhancing LLM Metacognition via Cognitive Pairwise Training DRAGged into Conflicts: Detecting and Addressing Conflicting Sources in Search-Augmented LLMs

Reference 53

Resolution: verified exact; arxiv_id, observed 2026-06-28T19:02:33.909346Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 27c8c8b0-526f-4e3c-a001-10c8cf58049e · outbound

This paper cites Justrl: Scaling a 1.5 b llm with a simple rl recipe.

Enhancing LLM Metacognition via Cognitive Pairwise Training Justrl: Scaling a 1.5 b llm with a simple rl recipe

Reference 54

Resolution: verified exact; arxiv_id, observed 2026-06-28T19:02:33.936053Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 8bdf3b5b-6178-47ba-a4a9-9eef55a067c6 · outbound

This paper cites Ur2: Unify rag and reasoning through reinforcement learning,.

Enhancing LLM Metacognition via Cognitive Pairwise Training Ur2: Unify rag and reasoning through reinforcement learning,

Reference 55

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30aa5c0e-6835-40d4-adb9-0b46876d988e · outbound

This paper cites OpenMathReasoning: A large-scale dataset for mathematical reasoning.

Enhancing LLM Metacognition via Cognitive Pairwise Training OpenMathReasoning: A large-scale dataset for mathematical reasoning

Reference 56

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de9bac03-2f72-459d-87e5-4b5db66b4fba · outbound

This paper cites Deepscaler: Surpassing o1-preview with a 1.5b model by scaling rl.

Enhancing LLM Metacognition via Cognitive Pairwise Training Deepscaler: Surpassing o1-preview with a 1.5b model by scaling rl

Reference 57

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8754b689-100b-48a9-b502-a305724c3190 · outbound

This paper cites ALCUNA: Large language models meet new knowledge,.

Enhancing LLM Metacognition via Cognitive Pairwise Training ALCUNA: Large language models meet new knowledge,

Reference 58

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2596288f-d4fb-4d71-9fd0-1e21afa726fe · outbound

This paper cites BBQ: A hand-built bias benchmark for question answering,.

Enhancing LLM Metacognition via Cognitive Pairwise Training BBQ: A hand-built bias benchmark for question answering,

Reference 59

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 510c8ede-dcf2-4fb3-93e5-06e22cbfafca · outbound

This paper cites Beyond the imitation game: Quantifying and extrapolating the capabilities of language models,.

Enhancing LLM Metacognition via Cognitive Pairwise Training Beyond the imitation game: Quantifying and extrapolating the capabilities of language models,

Reference 60

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b242b36f-a163-4102-8952-ff737cb88192 · outbound

This paper cites The Art of Saying No: Contextual Noncompliance in Language Models.

Enhancing LLM Metacognition via Cognitive Pairwise Training The Art of Saying No: Contextual Noncompliance in Language Models

Reference 61

Resolution: verified exact; arxiv_id, observed 2026-06-28T19:02:33.914764Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 17ff83c3-bbb6-40a6-9d5f-f4457095cf0e · outbound

This paper cites Won’t get fooled again: Answering questions with false premises,.

Enhancing LLM Metacognition via Cognitive Pairwise Training Won’t get fooled again: Answering questions with false premises,

Reference 62

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af7f8dda-8e5e-49b8-ab79-01530d7e72f7 · outbound

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

Enhancing LLM Metacognition via Cognitive Pairwise Training GPQA: A Graduate-Level Google-Proof Q&A Benchmark

Reference 63

Resolution: verified exact; local_arxiv, observed 2026-06-28T19:02:33.886938Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 390869fe-e783-4c9e-b84d-b8175df683cc · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Enhancing LLM Metacognition via Cognitive Pairwise Training Training Verifiers to Solve Math Word Problems

Reference 64

Resolution: verified exact; local_arxiv, observed 2026-06-28T19:02:33.894758Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation cc734824-a6f8-48ef-9c07-921805a7f29b · outbound

This paper cites Knowledge of knowledge: Exploring known- unknowns uncertainty with large language models,.

Enhancing LLM Metacognition via Cognitive Pairwise Training Knowledge of knowledge: Exploring known- unknowns uncertainty with large language models,

Reference 65

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2918d1a-655d-443e-be30-0de0d1c28bf9 · outbound

This paper cites MediQ: Question- asking LLMs and a benchmark for reliable interactive clinical reasoning,.

Enhancing LLM Metacognition via Cognitive Pairwise Training MediQ: Question- asking LLMs and a benchmark for reliable interactive clinical reasoning,

Reference 66

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f6f3b94-b327-4c5b-8412-19444b39f0f2 · outbound

This paper cites Measuring Massive Multitask Language Understanding.

Enhancing LLM Metacognition via Cognitive Pairwise Training Measuring Massive Multitask Language Understanding

Reference 67

Resolution: verified exact; local_arxiv, observed 2026-06-28T19:02:33.925386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 05c61c68-1a22-45b7-ac26-9509b07f215d · outbound

This paper cites Evaluating the moral beliefs encoded in LLMs,.

Enhancing LLM Metacognition via Cognitive Pairwise Training Evaluating the moral beliefs encoded in LLMs,

Reference 68

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f0d2a6b-01c7-424c-8bb2-cbfa76c76257 · outbound

This paper cites MuSiQue: Multihop questions via single-hop question composition,.

Enhancing LLM Metacognition via Cognitive Pairwise Training MuSiQue: Multihop questions via single-hop question composition,

Reference 69

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4b97692-3725-4f11-adea-1ede892a549b · outbound

This paper cites (QA)2: Question answering with questionable assumptions,.

Enhancing LLM Metacognition via Cognitive Pairwise Training (QA)2: Question answering with questionable assumptions,

Reference 70

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b15a0044-e5cf-4b89-9065-12387670db2d · outbound

This paper cites A dataset of information-seeking questions and answers anchored in research papers,.

Enhancing LLM Metacognition via Cognitive Pairwise Training A dataset of information-seeking questions and answers anchored in research papers,

Reference 71

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff3f6037-ebbd-4de5-bb89-69c38c2c9f0c · outbound

This paper cites SituatedQA: Incorporating extra-linguistic contexts into QA,.

Enhancing LLM Metacognition via Cognitive Pairwise Training SituatedQA: Incorporating extra-linguistic contexts into QA,

Reference 72

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 020ab70b-345c-4e92-b2d2-d44c20e7eb48 · outbound

This paper cites Know what you don’t know: Unanswerable questions for SQuAD,.

Enhancing LLM Metacognition via Cognitive Pairwise Training Know what you don’t know: Unanswerable questions for SQuAD,

Reference 73

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9aca73f5-75ae-4ec9-b117-543e1dce8d0d · outbound

This paper cites Benchmarking Hallucination in Large Language Models based on Unanswerable Math Word Problem.

Enhancing LLM Metacognition via Cognitive Pairwise Training Benchmarking Hallucination in Large Language Models based on Unanswerable Math Word Problem

Reference 74

Resolution: verified exact; arxiv_id, observed 2026-06-28T19:02:33.895497Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 87a0a974-f900-43b5-b4e8-7a7afb72d8e2 · outbound

This paper cites WorldSense: A Synthetic Benchmark for Grounded Reasoning in Large Language Models.

Enhancing LLM Metacognition via Cognitive Pairwise Training WorldSense: A Synthetic Benchmark for Grounded Reasoning in Large Language Models

Reference 75

Resolution: verified exact; arxiv_id, observed 2026-06-28T19:02:33.886009Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation abf0102e-ac5e-4a66-b00b-73e2c003fadc · outbound

This paper cites A coefficient of agreement for nominal scales,.

Enhancing LLM Metacognition via Cognitive Pairwise Training A coefficient of agreement for nominal scales,

Reference 76

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc117fe0-dd0b-499f-9a82-f756c76c995a · outbound

This paper cites The measurement of observer agreement for categorical data,.

Enhancing LLM Metacognition via Cognitive Pairwise Training The measurement of observer agreement for categorical data,

Reference 77

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73959039-848e-4cdc-99ba-858d46b7a98a · outbound

This paper cites Measuring nominal scale agreement among many raters,.

Enhancing LLM Metacognition via Cognitive Pairwise Training Measuring nominal scale agreement among many raters,

Reference 78

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05335121-b50c-4b1a-924d-b1738993691e · outbound

This paper cites Quagmires in sft-rl post-training: When high sft scores mislead and what to use instead.

Enhancing LLM Metacognition via Cognitive Pairwise Training Quagmires in sft-rl post-training: When high sft scores mislead and what to use instead

Reference 79

Resolution: verified exact; arxiv_id, observed 2026-06-28T19:02:33.832707Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f2d39fa9-1d82-46a6-a59a-91ebb8415b88 · outbound

This paper cites Beyond Two-Stage Training: Cooperative SFT and RL for LLM Reasoning.

Enhancing LLM Metacognition via Cognitive Pairwise Training Beyond Two-Stage Training: Cooperative SFT and RL for LLM Reasoning

Reference 80

Resolution: verified exact; local_arxiv, observed 2026-06-28T19:02:33.906107Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 42dd68ee-d222-4ae8-a4eb-d2e076113b97 · outbound

This paper cites The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models.

Enhancing LLM Metacognition via Cognitive Pairwise Training The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models

Reference 81

Resolution: verified exact; local_arxiv, observed 2026-06-28T19:02:33.878927Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a6ce62f4-2f0c-435d-9727-edc4d7977589 · outbound

This paper cites Enhancing LLM Reasoning with Iterative DPO: A Comprehensive Empirical Investigation.

Enhancing LLM Metacognition via Cognitive Pairwise Training Enhancing LLM Reasoning with Iterative DPO: A Comprehensive Empirical Investigation

Reference 82

Resolution: verified exact; arxiv_id, observed 2026-06-28T19:02:33.820741Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d0349acd-d333-4845-8385-e9e4ec6bbcf1 · outbound

This paper cites Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs.

Enhancing LLM Metacognition via Cognitive Pairwise Training Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 83

Resolution: verified exact; local_arxiv, observed 2026-06-28T19:02:33.922491Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f52aa683-347a-41b1-b4a1-96e1d3268983 · outbound

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

Enhancing LLM Metacognition via Cognitive Pairwise Training Tulu 3: Pushing Frontiers in Open Language Model Post-Training

Reference 84

Resolution: verified exact; local_arxiv, observed 2026-06-28T19:02:33.933275Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 9bd659e4-fe25-4360-b389-5b52ea14fdef · outbound

This paper cites Scaling Synthetic Data Creation with 1,000,000,000 Personas.

Enhancing LLM Metacognition via Cognitive Pairwise Training Scaling Synthetic Data Creation with 1,000,000,000 Personas

Reference 85

Resolution: verified exact; local_arxiv, observed 2026-06-28T19:02:33.900775Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation bef76b20-5982-4376-bab4-4beffeef4bfb · outbound

This paper cites The flan collection: Designing data and methods for effective instruction tuning,.

Enhancing LLM Metacognition via Cognitive Pairwise Training The flan collection: Designing data and methods for effective instruction tuning,

Reference 86

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b13a5645-3881-4eef-b975-4b12e6774f7e · outbound

This paper cites No robots.

Enhancing LLM Metacognition via Cognitive Pairwise Training No robots

Reference 87

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8b8d6ec-418d-442c-8b39-433afeead9dc · outbound

This paper cites Openassistant conversations-democratizing large language model alignment,.

Enhancing LLM Metacognition via Cognitive Pairwise Training Openassistant conversations-democratizing large language model alignment,

Reference 88

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3887d8e-8486-4f29-8db4-743526df9e16 · outbound

This paper cites Aya dataset: An open-access collection for multilingual instruction tuning,.

Enhancing LLM Metacognition via Cognitive Pairwise Training Aya dataset: An open-access collection for multilingual instruction tuning,

Reference 89

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65a97c2b-5886-440c-9cd5-8062bf0075e1 · outbound

This paper cites TableGPT: Towards Unifying Tables, Nature Language and Commands into One GPT.

Enhancing LLM Metacognition via Cognitive Pairwise Training TableGPT: Towards Unifying Tables, Nature Language and Commands into One GPT

Reference 90

Resolution: verified exact; arxiv_id, observed 2026-06-28T19:02:33.892949Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 10f6f86e-b98a-4838-9fcc-e75f0f78d3f3 · outbound

This paper cites WildChat: 1M ChatGPT Interaction Logs in the Wild.

Enhancing LLM Metacognition via Cognitive Pairwise Training WildChat: 1M ChatGPT Interaction Logs in the Wild

Reference 91

Resolution: verified exact; local_arxiv, observed 2026-06-28T19:02:33.875220Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ec15ae00-cfa5-4f1a-a14a-e9bf671ad825 · outbound

This paper cites Wizardcoder: Empower- ing code large language models with evol-instruct,.

Enhancing LLM Metacognition via Cognitive Pairwise Training Wizardcoder: Empower- ing code large language models with evol-instruct,

Reference 92

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dcbf4f63-cb42-4545-9a92-c9d2cde371c6 · outbound

This paper cites Wildguard: Open one-stop moderation tools for safety risks, jailbreaks, and refusals of llms,.

Enhancing LLM Metacognition via Cognitive Pairwise Training Wildguard: Open one-stop moderation tools for safety risks, jailbreaks, and refusals of llms,

Reference 93

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 841cab1c-4f80-4c4e-8ac5-8a21afe1e32c · outbound

This paper cites Wildteaming at scale: From in-the-wild jailbreaks to (adversarially) safer language models,.

Enhancing LLM Metacognition via Cognitive Pairwise Training Wildteaming at scale: From in-the-wild jailbreaks to (adversarially) safer language models,

Reference 94

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11a2b820-3a99-4a15-85ca-7566c57a6205 · outbound

This paper cites Sciriff: A resource to enhance language model instruction-following over scientific literature,.

Enhancing LLM Metacognition via Cognitive Pairwise Training Sciriff: A resource to enhance language model instruction-following over scientific literature,

Reference 95

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a889d61-35bc-4534-94a6-cd68941ec8b0 · outbound

This paper cites an unresolved cited work.

Enhancing LLM Metacognition via Cognitive Pairwise Training Unresolved cited work

Reference 96

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 550ad1d4-ac42-4ac7-8583-59784a9471c9 · outbound

This paper cites an unresolved cited work.

Enhancing LLM Metacognition via Cognitive Pairwise Training Unresolved cited work

Reference 97

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c923e4e-db04-4b16-9032-a24d3db713bf · outbound

This paper cites I don’t know.

Enhancing LLM Metacognition via Cognitive Pairwise Training I don’t know

Reference 98

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7df0871e-ed7c-4dce-bdd4-6b37b4390253 · outbound

This paper cites For base checkpoints, the dataset loader extracts the raw prompt text from the stored chat-style field and tokenizes it directly, instead of applying a chat template.

Enhancing LLM Metacognition via Cognitive Pairwise Training For base checkpoints, the dataset loader extracts the raw prompt text from the stored chat-style field and tokenizes it directly, instead of applying a chat template

Reference 99

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f1a6f02-4963-4586-8152-bfcfc5519889 · outbound

This paper cites For each promptx, the policy samples a group ofGresponses{y i}G i=1 from vLLM [52]; in the main Math-RL scriptG= 16, temperature is 0.9, andtop-p=0.95.

Enhancing LLM Metacognition via Cognitive Pairwise Training For each promptx, the policy samples a group ofGresponses{y i}G i=1 from vLLM [52]; in the main Math-RL scriptG= 16, temperature is 0.9, andtop-p=0.95

Reference 100

Resolution: unresolved; no resolver link, observed 2026-06-28T19:01:18.153145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers