Low-probability Tokens Sustain Exploration in Reinforcement Learning with Verifiable Reward
Paper
• 2510.03222 • Published
• 75
LLM papers
-
-
In-the-Flow Agentic System Optimization for Effective Planning and Tool Use
Paper • 2510.05592 • Published • 107 -
Less is More: Recursive Reasoning with Tiny Networks
Paper • 2510.04871 • Published • 509 -
Multi-Agent Tool-Integrated Policy Optimization
Paper • 2510.04678 • Published • 31 -
EPO: Entropy-regularized Policy Optimization for LLM Agents Reinforcement Learning
Paper • 2509.22576 • Published • 135 -
A Survey of Reinforcement Learning for Large Reasoning Models
Paper • 2509.08827 • Published • 190 -
AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning
Paper • 2509.08755 • Published • 57 -
GEM: A Gym for Agentic LLMs
Paper • 2510.01051 • Published • 90 -
Agentic Entropy-Balanced Policy Optimization
Paper • 2510.14545 • Published • 106 -
Dyna-Mind: Learning to Simulate from Experience for Better AI Agents
Paper • 2510.09577 • Published • 8 -
Can LLMs Guide Their Own Exploration? Gradient-Guided Reinforcement Learning for LLM Reasoning
Paper • 2512.15687 • Published • 21 -
Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models
Paper • 2512.13607 • Published • 36 -
Adaptation of Agentic AI
Paper • 2512.16301 • Published • 106 -
SAGE: Training Smart Any-Horizon Agents for Long Video Reasoning with Reinforcement Learning
Paper • 2512.13874 • Published • 17 -
Recursive Language Models
Paper • 2512.24601 • Published • 89 -
Token-Level LLM Collaboration via FusionRoute
Paper • 2601.05106 • Published • 40 -
Collaborative Multi-Agent Test-Time Reinforcement Learning for Reasoning
Paper • 2601.09667 • Published • 91 -
The Flexibility Trap: Why Arbitrary Order Limits Reasoning Potential in Diffusion Language Models
Paper • 2601.15165 • Published • 72 -
Behavior Knowledge Merge in Reinforced Agentic Models
Paper • 2601.13572 • Published • 24 -
Learning to Discover at Test Time
Paper • 2601.16175 • Published • 42 -
Endless Terminals: Scaling RL Environments for Terminal Agents
Paper • 2601.16443 • Published • 17 -
Teaching Models to Teach Themselves: Reasoning at the Edge of Learnability
Paper • 2601.18778 • Published • 40 -
Linear representations in language models can change dramatically over a conversation
Paper • 2601.20834 • Published • 21 -
Self-Distillation Enables Continual Learning
Paper • 2601.19897 • Published • 26 -
RLAnything: Forge Environment, Policy, and Reward Model in Completely Dynamic RL System
Paper • 2602.02488 • Published • 32 -
Self-Hinting Language Models Enhance Reinforcement Learning
Paper • 2602.03143 • Published • 29 -
Experiential Reinforcement Learning
Paper • 2602.13949 • Published • 67 -
Multi-agent cooperation through in-context co-player inference
Paper • 2602.16301 • Published • 23