mlsanityData to 7 Oct 2026

Learning to Learn from Language Feedback with Social Meta-Learning

arXiv 2602.16488 ↗First posted 18 Feb 2026cs.CL cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

Large language models (LLMs) often struggle to learn from corrective feedback within a conversational context. They are rarely proactive in soliciting this feedback, even when faced with ambiguity, which can make their dialogues feel static, one-sided, and lacking the adaptive qualities of human conversation. To address these limitations, we draw inspiration from social meta-learning (SML) in humans - the process of learning how to learn from others. We formulate SML as a finetuning methodology, training LLMs to solicit and learn from language feedback in simulated pedagogical dialogues, where static tasks are converted into interactive social learning problems. SML effectively teaches models to use conversation to solve problems they are unable to solve in a single turn. This capability generalises across domains; SML on math problems produces models that better use feedback to solve coding problems and vice versa. Furthermore, despite being trained only on fully-specified problems, these models are better able to solve underspecified tasks where critical information is revealed over multiple turns. When faced with this ambiguity, SML-trained models make fewer premature answer attempts and are more likely to ask for the information they need. This work presents a scalable approach to developing AI systems that effectively learn from language feedback.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 39 of its 44 references that are in the map. First posted on arXiv 18 Feb 2026.

Builds on

39 of 44 references.

References · 39

  1. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  2. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Codecited by 1,906
  3. 2022STaR: Bootstrapping Reasoning With Reasoningcited by 895
  4. 2023RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignmentcited by 672
  5. 2025SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-trainingcited by 655
  6. 2023A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPTcited by 612
  7. 2024Training Language Models to Self-Correct via Reinforcement Learningcited by 405
  8. 2025LLMs Get Lost In Multi-Turn Conversationcited by 400
  9. 2023Understanding the Effects of RLHF on LLM Generalisation and Diversitycited by 386
  10. 2025Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRscited by 373
  11. 2023MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedbackcited by 293
  12. 2024Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Modelscited by 277
27 more
  1. 2024ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RLcited by 212
  2. 2024A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systemscited by 170
  3. 2024Recursive Introspection: Teaching Language Model Agents How to Self-Improvecited by 162
  4. 2023Training Language Models with Language Feedback at Scalecited by 125
  5. 2025CollabLLM: From Passive Responders to Active Collaboratorscited by 117
  6. 2025SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Taskscited by 108
  7. 2024STaR-GATE: Teaching Language Models to Ask Clarifying Questionscited by 99
  8. 2025SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learningcited by 89
  9. 2024Can large language models explore in-context?cited by 75
  10. 2024Modeling Future Conversation Turns to Teach LLMs to Ask Clarifying Questionscited by 70
  11. 2025Beyond Single-Turn: A Survey on Multi-Turn Interactions with Large Language Modelscited by 58
  12. 2025OpenCodeInstruct: A Large-scale Instruction Tuning Dataset for Code LLMscited by 57
  13. 2025QuestBench: Can LLMs ask the right question to acquire information in reasoning tasks?cited by 56
  14. 2021The Difficulty of Passive Learning in Deep Reinforcement Learningcited by 50
  15. 2022Inferring Rewards from Language in Contextcited by 50
  16. 2020Emergent Social Learning via Multi-agent Reinforcement Learningcited by 44
  17. 2024Understanding User Experience in Large Language Model Interactionscited by 43
  18. 2025Thinking vs. Doing: Agents that Reason by Scaling Test-Time Interactioncited by 34
  19. 2024Cultural Evolution of Cooperation among LLM Agentscited by 30
  20. 2025Interleaved Reasoning for Large Language Models via Reinforcement Learningcited by 21
  21. 2024When LLMs Play the Telephone Game: Cultural Attractors as Conceptual Tools to Evaluate LLMs in Multi-turn Settingscited by 17
  22. 2024In-context Exploration-Exploitation for Reinforcement Learningcited by 16
  23. 2017Observational Learning by Reinforcement Learningcited by 12
  24. 2025Done Is Better than Perfect: Unlocking Efficient Reasoning by Structured Multi-Turn Decompositioncited by 11
  25. 2025Formalizing Learning from Language Feedback with Provable Guaranteescited by 10
  26. 2024Artificial Generational Intelligence: Cultural Accumulation in Reinforcement Learningcited by 8
  27. 2025Broaden your SCOPE! Efficient Multi-turn Conversation Planning for LLMs with Semantic Spacecited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026What Drives Interactive Improvement from Feedback?cited by 1