14 papers
RSIPO: Recursive Self-Improving Policy Optimization for Agentic Reinforcement Learning via Skill-Policy Co-Evolution
Fan Zhang, Hao Wu, Jinyang Wu +7
Recent focus in agentic reinforcement learning (RL) seeks to improve credit assignment in long-horizon tasks. One promising direction combines reinforcement learning with verifiabl…
SCAD: Structured Credit Assignment and Distillation for Long-Horizon Agents
Shangyang Wu, Shuai Zhao, Ziyue Zhu +3
Training long-horizon agents to solve complex tasks requires effective supervision over extended interaction sequences. However, sparse terminal rewards obscure intermediate contri…
AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning
Zi-Han Wang, Zhengxi Lu, Zhiyuan Yao +10
Reinforcement learning (RL) with verifiable rewards constructs trajectory-level advantage estimates, yet it often fails to credit the few pivotal decisions that determine outcomes…
PCSD: Persistent Consistency for Self-Distillation in Agentic Reinforcement Learning
Chunji Lv, Yangguang Wei, Junlin Liu +6
Large language model agents have shown strong potential in complex interactive tasks, yet their reinforcement learning (RL) is often hindered by sparse rewards, as a long multi-tur…
From Proprietary to Open-Source: Bridging the Distribution Gap via Multi-Agent Protocol Distillation in Agentic Search
Junlin Liu, Jiangwang Chen, Zixin Song +7
Agentic search enables large language models to solve knowledge-intensive tasks by interleaving multi-step reasoning with retrieval, yet optimizing this with outcome-based reinforc…
SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning
Jinyang Wu, Shuo Yang, Zhengxi Lu +8
Large language models are increasingly trained as interactive agents for long-horizon tasks involving multi-turn interaction, tool use, and environment feedback. Outcome-based rein…
OPID: On-Policy Skill Distillation for Agentic Reinforcement Learning
Shuo Yang, Jinyang Wu, Zhengxi Lu +8
Outcome-based reinforcement learning provides a stable optimization backbone for language agents, but its sparse trajectory-level rewards provide little guidance on which intermedi…
Learning to Adapt SFT Data for Better Reasoning Generalization
Lisong Sun, Li Wang, Chen Zhang +4
Large language models (LLMs) have achieved remarkable progress, with post-training playing a crucial role in enhancing their reasoning capabilities. Among post-training paradigms,…
Maestro: Reinforcement Learning to Orchestrate Hierarchical Model-Skill Ensembles
Jinyang Wu, Guocheng Zhai, Ruihan Jin +7
The proliferation of large language models (LLMs) and modular skills has endowed autonomous agents with increasingly powerful capabilities. Existing frameworks typically rely on mo…
Implicit Hierarchical GRPO: Decoupling Tool Invocation from Execution for Tool-Integrated Mathematical Reasoning
Li Wang, Xiaohan Wang, Xiaodong Lu +5
Large language models (LLMs) have increasingly leveraged tool invocation to enhance their reasoning capabilities. However, existing approaches typically tightly couple tool invocat…
SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization
Zhengxi Lu, Zhiyuan Yao, Jinyang Wu +7
Agent skills, structured packages of procedural knowledge and executable resources that agents dynamically load at inference time, have become a reliable mechanism for augmenting L…
Self-Distilled Agentic Reinforcement Learning
Zhengxi Lu, Zhiyuan Yao, Zhuowen Han +8
Reinforcement learning (RL) has emerged as a central paradigm for post-training LLM agents, yet its trajectory-level reward signal provides only coarse supervision for long-horizon…
Double: Breaking the Acceleration Limit via Double Retrieval Speculative Parallelism
Yuhao Shen, Tianyu Liu, Junyi Shen +4
Parallel Speculative Decoding (PSD) accelerates traditional Speculative Decoding (SD) by overlapping draft generation with verification. However, it remains hampered by two fundame…
Atlas: Orchestrating Heterogeneous Models and Tools for Multi-Domain Complex Reasoning
Jinyang Wu, Guocheng Zhai, Ruihan Jin +5
The integration of large language models (LLMs) with external tools has significantly expanded the capabilities of AI agents. However, as the diversity of both LLMs and tools incre…