4 papers
MDSKILL: Learning to Internalize Skill Memory through Multi-View Distillation for Efficient Dynamic Agent Self-Evolution
Dian Jin, Jinluan Yang, Kairong Han +9
Skill memories encode past experiences as textual prompts to improve reinforcement learning (RL) for self-evolving agents. Complementing RL, On-Policy Self-Distillation (OPSD) prov…
SkillScaffold: Scaffolding Agentic Reinforcement Learning with Policy-Adaptive Skill Credit Assignment and Selective Injection
Wenlin Zhong, Hao Wang, Kun Yuan +6
Agentic reinforcement learning (RL) enables large language models (LLMs) to learn from multi-turn interactions with verifiable outcomes. Textual skills can improve exploration by d…
Towards Efficient Reasoning: Learning Causal Shortcuts for Diffusion Language Models
Dian Jin, Kairong Han, Baohong Li +5
Diffusion Language Models (DLMs) have attracted significant attention for their strong reasoning ability. However, under a bidirectional attention mechanism, DLMs operate over an e…
Personalizing Large Language Model Agents with Small Policy Models
Dian Jin, Zhi Zhang, Huichao Li +3
Large language model (LLM) agents can retrieve memory, call tools, ask clarifying questions, and vary response style, yet adapting these execution decisions to an individual user r…