LeAct: Learning to Reason from Expert Actions

• URL: http://arxiv.org/abs/2607.21856v1
• Date: Thu, 23 Jul 2026 22:50:23 GMT
• Title: LeAct: Learning to Reason from Expert Actions
• Abstract summary: Expert systems produce near-optimal actions across diverse domains.<n>We show how to distill expert knowledge into a student that generalizes beyond the demonstrated actions.<n>We present a principled framework and the result: expert systems become a categorically new source of reasoning teachers for foundation models.
• Score: 55.48554303260889
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Modern reasoning models depend on reasoning data, today sourced from human annotations or distilled from stronger LLMs. However, a rich and largely untapped source of supervision lies in expert systems (e.g., game engines, classical planners, theorem provers), which routinely produce near-optimal actions across diverse domains. But these experts are silent: they commit to an action without writing down the chain of thought (CoT) behind it. Recovering that CoT as natural-language reasoning would distill expert knowledge into a student that generalizes beyond the demonstrated actions. We treat it as a latent variable and study how to recover it from the action alone. Our approach, LeAct (Learning to reason from Actions), optimizes this latent variable: the student samples candidate CoTs for each expert action, and we retain those that measurably improve its own probability of recovering the action. Across imperfect-information games at multiple scales and a simulated robotics benchmark, LeAct reaches the solver's numerical floor on small enumerable games. At larger scale, it is $5\times$ closer to the solver than the strongest expert-iteration baseline. At Flop Hold'em ($\sim 10^9$ infosets), LeAct wins head-to-head by $+60$ mbb/g, and on the robotics probe it is the only training recipe that improves on direct imitation. We present a principled framework and the result: expert systems become a categorically new source of reasoning teachers for foundation models.

Related papers

• Expanding the Capabilities of Reinforcement Learning via Text Feedback [49.561885700139676]
  We formalize a multi-turn RL setup, RL from Text Feedback (RLTF), where text feedback is available during training but not at inference.<n>To do this, we propose two methods: Self Distillation (RLTF-SD), which trains the single-turn policy to match its own feedback-conditioned second-turn generations; and Feedback Modeling (RLTF-FM), which predicts the feedback as an auxiliary objective.<n>Our results show that both methods consistently outperform strong baselines across benchmarks.
  arXiv  Detail & Related papers  (2026-02-02T18:56:56Z)
• LLM CHESS: Benchmarking Reasoning and Instruction-Following in LLMs through Chess [30.797553771114746]
  We introduce LLM CHESS, an evaluation framework designed to probe the generalization of reasoning and instruction-following abilities in large language models (LLMs)<n>We rank over 50 open and closed source models by playing against a random opponent using a range of behavioral metrics, including move quality, move legality, hallucinated actions, and game duration.<n>For a subset of top reasoning models, we derive an Elo estimate by playing against a chess engine with variably configured skill, which allows for comparisons between models in an easily understandable way.
  arXiv  Detail & Related papers  (2025-12-01T18:51:08Z)
• Multi-Agent Evolve: LLM Self-Improve through Co-evolution [53.00458074754831]
  Reinforcement Learning (RL) has demonstrated significant potential in enhancing the reasoning capabilities of large language models (LLMs)<n>Recent Self-Play RL methods, inspired by the success of the paradigm in games and Go, aim to enhance LLM reasoning capabilities without human-annotated data.<n>We propose Multi-Agent Evolve (MAE), a framework that enables LLMs to self-evolve in solving diverse tasks, including mathematics, reasoning, and general knowledge Q&A.
  arXiv  Detail & Related papers  (2025-10-27T17:58:02Z)
• Off-Trajectory Reasoning: Can LLMs Collaborate on Reasoning Trajectory? [13.980638430366625]
  Reasoning LLMs are trained to verbalize their reasoning process, yielding strong gains on complex tasks.<n>A key prerequisite is the ability to assess the usefulness and build on another model's partial thinking.<n>This paper investigates the question: can standard solo-reasoning training pipelines deliver desired off-trajectory behaviors?
  arXiv  Detail & Related papers  (2025-10-07T19:42:50Z)
• Can Large Models Teach Student Models to Solve Mathematical Problems Like Human Beings? A Reasoning Distillation Method via Multi-LoRA Interaction [6.695255921627406]
  Large Language Models (LLMs) have strong mathematical reasoning abilities but rely on hundreds of billions of parameters.<n>Existing methods typically leverage LLMs to generate massive amounts of data for cramming training.<n>We propose a novel method based on the multi-LoRA Interaction for mathematical reasoning Distillation (LoRID)<n>LoRID achieves state-of-the-art performance, especially on the GSM8K dataset.
  arXiv  Detail & Related papers  (2025-08-18T15:56:10Z)
• Generalist Reward Models: Found Inside Large Language Models [50.7432354447554]
  We show that a powerful reward model is already latently present within any Large Language Models (LLMs) trained via standard next-token prediction.<n>We prove that this endogenous reward is not a reward function learned through offline inverse reinforcement learning.<n>We also prove that subsequent reinforcement learning using this endogenous reward leads to a policy with a provably superior error bound compared to the base model.
  arXiv  Detail & Related papers  (2025-06-29T13:45:54Z)
• Distilling LLM Agent into Small Models with Retrieval and Code Tools [65.73762766854192]
  Agent Distillation is a framework for transferring reasoning capability and task-solving behavior from large language models into small language models.<n>Our results show that sLMs as small as 0.5B, 1.5B, 3B parameters can achieve performance competitive with next-tier larger 1.5B, 3B, 7B models.
  arXiv  Detail & Related papers  (2025-05-23T08:20:15Z)
• Self-Explore: Enhancing Mathematical Reasoning in Language Models with Fine-grained Rewards [42.065997425172974]
  Training on large amounts of rationales (i.e., CoT Fine-tuning) is effective at improving the reasoning capabilities of large language models (LLMs) We propose Self-Explore, where the LLM is tasked to explore the first wrong step within the rationale and use such signals as fine-grained rewards for further improvement. On the GSM8K and MATH test set, Self-Explore achieves 11.57% and 2.89% improvement on average across three LLMs compared to supervised fine-tuning (SFT)
  arXiv  Detail & Related papers  (2024-04-16T07:30:11Z)
• Democratizing Reasoning Ability: Tailored Learning from Large Language Model [97.4921006089966]
  We propose a tailored learning approach to distill such reasoning ability to smaller LMs. We exploit the potential of LLM as a reasoning teacher by building an interactive multi-round learning paradigm. To exploit the reasoning potential of the smaller LM, we propose self-reflection learning to motivate the student to learn from self-made mistakes.
  arXiv  Detail & Related papers  (2023-10-20T07:50:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.