mlsanityData to 7 Oct 2026

Before you <think>, monitor: Implementing Flavell's metacognitive framework in LLMs

arXiv 2510.16374 ↗First posted 18 Oct 2025cs.AIcited by 3

On the map: LLM reasoning → Test-time compute and efficient thinking

Abstract (arXiv)

Current approaches to enhancing LLM reasoning follows two isolated paradigms: Monitor-Generate methods like Plan-and-Solve (Wang et al., 2023) and SELF-DISCOVER (Zhou et al., 2024) excel at strategic planning but lack mechanisms to verify whether selected strategies succeed; while Generate-Verify approaches like Self-Verification (Weng et al., 2022) and SELF-REFINE (Madaan et al., 2023) iteratively refine outputs but commence generation blindly without task assessment. This separation creates inefficiencies -- strategies fail without feedback, and refinement occurs without strategic grounding. We address this gap by implementing Flavell's cognitive monitoring model (1979) from the broader Monitor-Generate-Verify framework (Oh and Gobet, 2025), operationalising it as a three-phase iterative system. On GSM8K, preliminary results show 75.42% accuracy versus 68.44% for SELF-REFINE and 67.07% for Self-Verification, while requiring fewer attempts (1.3 vs 2.0) at 27-37% increased inference cost. These initial findings suggest upfront monitoring produces higher-quality initial solutions that reduce refinement needs, though evaluation beyond arithmetic reasoning is needed to establish generalisability.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning. Builds on 23 of its 32 references that are in the map. First posted on arXiv 18 Oct 2025.

Builds on

23 of 32 references.

Closest ancestors · 9

Same direction, newest first

  1. 2025Learning from Peers in Reasoning Models12 May
  2. 2025Scalable Chain of Thoughts via Elastic Reasoning8 May
  3. 2025ReVISE: Learning to Refine at Test-Time via Intrinsic Self-Verification20 Feb
  4. 2024Meta Reasoning for Large Language Models17 Jun
  5. 2024Small Language Models Need Strong Verifiers to Self-Correct Reasoning26 Apr
  6. 2024On the Self-Verification Limitations of Large Language Models on Reasoning and Planning Tasks12 Feb
  7. 2024V-STaR: Training Verifiers for Self-Taught Reasoners9 Feb
  8. 2024Self-Discover: Large Language Models Self-Compose Reasoning Structures6 Feb
  9. 2023Self-Refine: Iterative Refinement with Self-Feedback30 Mar

Other references · 14

  1. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  2. 2023Representation Engineering: A Top-Down Approach to AI Transparencycited by 1,239
  3. 2023Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMscited by 946
  4. 2023Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Modelscited by 550
  5. 2022Large Language Models are Better Reasoners with Self-Verificationcited by 304
  6. 2024LLMs Can't Plan, But Can Help Planning in LLM-Modulo Frameworkscited by 178
  7. 2024Looking Inward: Language Models Can Learn About Themselves by Introspectioncited by 105
  8. 2024Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem Solvingcited by 82
  9. 2023Aligning Large Language Models with Human Preferences through Representation Engineeringcited by 71
  10. 2025Language Models Are Capable of Metacognitive Monitoring and Control of Their Internal Activationscited by 37
  11. 2025Metacognition and Uncertainty Communication in Humans and Large Language Modelscited by 23
  12. 2024Strategic Chain-of-Thought: Guiding Accurate Reasoning in LLMs through Strategy Elicitationcited by 19
2 more
  1. 2024HYBRIDMIND: Meta Selection of Natural Language and Symbolic Language for Enhanced LLM Reasoningcited by 11
  2. 2025Decomposing Elements of Problem Solving: What "Math" Does RL Teach?cited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMscited by 4
  2. 2026Think2: Grounded Metacognitive Reasoning in Large Language Modelscited by 1
  3. 2026Metacognition in LLMs: Foundations, Progress, and Opportunitiescited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2026LLMs Know When They Know, but Do Not Act on It: A Metacognitive Harness for Test-time Scaling
  2. 2025Monitor-Generate-Verify (MGV): Formalising Metacognitive Theory for Language Model Reasoning
  3. 2026Metacognition as Reward: Reinforcing LLM Reasoning via Knowledge and Regulation Signals
  4. 2026Beyond Meta-Reasoning: Metacognitive Consolidation for Self-Improving LLM Reasoning
  5. 2026From Meta-Thought to Execution: Cognitively Aligned Post-Training for Generalizable and Reliable LLM Reasoning
  6. 2025Metacognitive Reuse: Turning Recurring LLM Reasoning Into Concise Behaviors
  7. 2025Cognitive Foundations for Reasoning and Their Manifestation in LLMs
  8. 2026Enhancing LLM Metacognition via Cognitive Pairwise Training