7 papers
Prune-OPD: Efficient and Reliable On-Policy Distillation for Long-Horizon Reasoning
Zhicheng Yang, Zhijiang Guo, Yifan Song +5
On-policy distillation (OPD) leverages dense teacher rewards to enhance reasoning models. However, scaling OPD to long-horizon tasks exposes a critical flaw: as the student's gener…
Depth-Breadth Synergy in RLVR: Unlocking LLM Reasoning Gains with Adaptive Exploration
Zhicheng Yang, Zhijiang Guo, Yinya Huang +6
Reinforcement Learning with Verifiable Reward (RLVR) is a powerful method for enhancing the reasoning abilities of Large Language Models, but its full potential is limited by a lac…
Accordion-Thinking: Self-Regulated Step Summaries for Efficient and Readable LLM Reasoning
Zhicheng Yang, Zhijiang Guo, Yinya Huang +5
Scaling test-time compute via long Chain-of-Thought unlocks remarkable gains in reasoning capabilities, yet it faces practical limits due to the linear growth of KV cache and quadr…
From Prefix Cache to Fusion RAG Cache: Accelerating LLM Inference in Retrieval-Augmented Generation
Jiahao Wang, Weiyu Xie, Mingxing Zhang +10
Retrieval-Augmented Generation enhances Large Language Models by integrating external knowledge, which reduces hallucinations but increases prompt length. This increase leads to hi…
Critique to Verify: Accurate and Honest Test-Time Scaling with RL-Trained Verifiers
Zhicheng Yang, Zhijiang Guo, Yinya Huang +4
Test-time scaling via solution sampling and aggregation has become a key paradigm for improving the reasoning performance of Large Language Models (LLMs). While reward model select…
TreeRPO: Tree Relative Policy Optimization
Zhicheng Yang, Zhijiang Guo, Yinya Huang +3
Large Language Models (LLMs) have shown remarkable reasoning capabilities through Reinforcement Learning with Verifiable Rewards (RLVR) methods. However, a key limitation of existi…