4 papers
Propose, Verify, Commit: Evidence-Grounded Memory for Long-Horizon Multi-Actor Conversations
Zihao Lu, Zhihang Yuan, Lei Shi +1
Memory enables language model agents to use information beyond their context windows, but maintaining and accessing this information reliably remains difficult. Long-horizon conver…
LANPO: Bootstrapping Language and Numerical Feedback for Reinforcement Learning in LLMs
Ang Li, Yifei Wang, Zhihang Yuan +2
Reinforcement learning in large language models (LLMs) often relies on scalar rewards, a practice that discards valuable textual rationale buried in the rollouts, forcing the model…
Know When to Explore: Difficulty-Aware Certainty as a Guide for LLM Reinforcement Learning
Ang Li, Zhihang Yuan, Yang Zhang +2
Reinforcement Learning with Verifiable Feedback (RLVF) has become a key technique for enhancing the reasoning abilities of Large Language Models (LLMs). However, its reliance on sp…
SplitMeanFlow: Interval Splitting Consistency in Few-Step Generative Modeling
Yi Guo, Wei Wang, Zhihang Yuan +8
Generative models like Flow Matching have achieved state-of-the-art performance but are often hindered by a computationally expensive iterative sampling process. To address this, r…