arXiv Machine Learning
Jul 27
LeAct: Learning to Reason from Expert Actions
arXiv:2607. 21856v1 Announce Type: new Abstract: Modern reasoning models depend on reasoning data, today sourced from human annotations or distilled from stronger LLMs.
Discovering High-Quality Chess Puzzles with Offline Reinforcement Learning
arXiv:2608. 14851v1 Announce Type: new Abstract: Learning and skill mastery require extensive and deliberate practice.
Related stories
arXiv AI
6d ago
Beyond Outcome Rewards: Step-Level Self-Distilled Policy Optimization for Deep Search Agents
arXiv:2608. 12764v1 Announce Type: cross Abstract: Deep search agents operate over trajectories spanning dozens of steps, yet standard reinforcement learning provides only a single outcome reward per trajectory, which is far too sparse for effective credit assignment.
arXiv AI
Jul 20
Understanding Reasoning from Pretraining to Post-Training
arXiv:2607. 16097v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become central to improving large language models (LLMs) on complex reasoning tasks, yet RL post-training is largely studied in isolation from the pretraining that precedes it.
arXiv AI
1d ago
Effective Personalized AI Tutors via LLM-Guided Reinforcement Learning
arXiv:2608. 16907v1 Announce Type: cross Abstract: Generative AI (GenAI) is rapidly reshaping education by unlocking the potential for personalized tutoring.
arXiv AI
Jul 3
Playing 20 Question Game with Policy-Based Reinforcement Learning
arXiv:1808. 07645v5 Announce Type: replace-cross Abstract: The 20 Questions (Q20) game is a well known game which encourages deductive reasoning and creativity.
arXiv Machine Learning
Jul 1
Teaching Models to Teach Themselves: Reasoning at the Edge of Learnability
arXiv:2601. 18778v3 Announce Type: replace Abstract: RL methods for scaling large reasoning models stall on datasets with low initial success rates, and thus little training signal.
arXiv Machine Learning
Aug 3
Learning Stateful Predictive Knowledge From Experience
arXiv:2607. 28638v1 Announce Type: cross Abstract: As large language model (LLM) agents increasingly learn from experience, they primarily rely on trajectory-level reflection to extract insights.
arXiv AI
Jun 16
RL-Index: Reinforcement Learning for Retrieval Index Reasoning
arXiv:2606. 16316v1 Announce Type: cross Abstract: Retrieving external knowledge is essential for solving real-world tasks, yet it remains challenging when the relationship between a query and its relevant knowledge involves implicit and complex reasoning beyond surface-level semantic or lexical matching (e.
arXiv AI
Aug 7
Search2Skill: Skill Distillation Beyond Knowledge Boundaries Via Rubric-Based Reinforcement Learning
arXiv:2608. 05245v1 Announce Type: new Abstract: Reusable skills, which encapsulate the procedural knowledge required to solve real-world professional tasks, offer LLM-based agents a path toward self-evolution in expert domains.
arXiv AI
Jul 2
Play Like Champions: Counterfactual Feedback Generation in Latent Space
arXiv:2607. 00190v1 Announce Type: cross Abstract: Recent advances in reinforcement learning have produced superhuman agents across a wide range of competitive games.
arXiv AI
Jul 14
People use fast and flat simulation to reason about new games
arXiv:2510. 11503v2 Announce Type: replace-cross Abstract: Games have long been a microcosm for studying planning and reasoning in both natural and artificial intelligence (AI), often focusing on expert-level or even super-human play.
arXiv AI
Jun 4
DeliChess: A Multi-party Dialogue Dataset for Deliberation in Chess Puzzle Solving
arXiv:2606. 04987v1 Announce Type: cross Abstract: Multi-party dialogue is a critical setting for studying collaborative reasoning and decision-making, yet existing datasets rarely focus on structured, in-depth complex reasoning tasks.