Categories

131 个页面

Reading

Self-Guided Function Calling in Large Language Models via Stepwise Experience Recall

Think in Blocks：Adaptive Reasoning from Direct Response to Deep Reasoning

Your Reward Function for RL is Your Best PRM for Search：Unifying RL and Search-Based TTS

未命名

MemAgent：Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent

Reinforcement Learning with Rubric Anchors

BEYOND PASS@1：SELF-PLAY WITH VARIATIONAL PROBLEM SYNTHESIS SUSTAINS RLVR

Beyond the 80 20 Rule：High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning

CausalPlan：Empowering Efficient LLM Multi-Agent Collaboration Through Causality-Driven Planning

Small Language Models are the Future of Agentic AI