10 papers
Experience Augmented Policy Optimization for LLM Reasoning
Jinda Lu, Kexin Huang, Junkang Wu +7
Reinforcement Learning with Verifiable Rewards (RLVR) is a powerful paradigm for improving the reasoning capabilities of large language models (LLMs). However, existing RLVR method…
ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples
Kexin Huang, Junkang Wu, Jinda Lu +7
Reinforcement learning (RL) has significantly enhanced the reasoning capabilities of large language models (LLMs), yet the training process remains notoriously fragile. In this wor…
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…
FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization
Chiyu Ma, Shuo Yang, Kexin Huang +7
We present Future-KL Influenced Policy Optimization (FIPO), a reinforcement learning algorithm designed to overcome reasoning bottlenecks in large language models. While GRPO style…
Bridging Perception and Reasoning: Token Reweighting for RLVR in Multimodal LLMs
Jinda Lu, Junkang Wu, Jinghan Li +6
Extending Reinforcement Learning with Verifiable Rewards (RLVR) to multimodal large language models (MLLMs) faces a fundamental challenge: their responses inherently interleave per…
Sparse but Critical: A Token-Level Analysis of Distributional Shifts in RLVR Fine-Tuning of LLMs
Haoming Meng, Kexin Huang, Shaohang Wei +6
Reinforcement learning with verifiable rewards (RLVR) has significantly improved reasoning in large language models (LLMs), yet the token-level mechanisms underlying these improvem…
ToolTree: Efficient LLM Agent Tool Planning via Dual-Feedback Monte Carlo Tree Search and Bidirectional Pruning
Shuo Yang, Soyeon Caren Han, Yihao Ding +2
Large Language Model (LLM) agents are increasingly applied to complex, multi-step tasks that require interaction with diverse external tools across various domains. However, curren…
Exploring Knowledge Purification in Multi-Teacher Knowledge Distillation for LLMs
Ruihan Jin, Pengpeng Shao, Zhengqi Wen +5
Knowledge distillation has emerged as a pivotal technique for transferring knowledge from stronger large language models (LLMs) to smaller, more efficient models. However, traditio…
Spark: Strategic Policy-Aware Exploration via Dynamic Branching for Long-Horizon Agentic Learning
Jinyang Wu, Shuo Yang, Changpeng Yang +4
Reinforcement learning has empowered large language models to act as intelligent agents, yet training them for long-horizon tasks remains challenging due to the scarcity of high-qu…