11 papers
Reference-Sampled Boltzmann Projection for KL-Regularized RLVR: Target-Matched Weighted SFT, Finite One-Shot Gaps, and Policy Mirror Descent
Yao Shu, Chenxing Wei, Hongbin Lin +2
Online reinforcement learning with verifiable rewards (RLVR) turns checkable outcomes into a scalable training signal, but it keeps rollout generation, verifier scoring, and refere…
Scheduling Your LLM Reinforcement Learning with Reasoning Trees
Hong Wang, Zhezheng Hao, Jian Luo +6
Using Reinforcement Learning with Verifiable Rewards (RLVR) to optimize Large Language Models (LLMs) can be conceptualized as progressively editing a query's `Reasoning Tree'. This…
MEMO: Memory-Augmented Model Context Optimization for Robust Multi-Turn Multi-Agent LLM Games
Yunfei Xie, Kevin Wang, Bobby Cheng +9
Multi-turn, multi-agent LLM game evaluations often exhibit substantial run-to-run variance. In long-horizon interactions, small early deviations compound across turns and are ampli…
SAGE: Multi-Agent Self-Evolution for LLM Reasoning
Yulin Peng, Xinxin Zhu, Chenxing Wei +4
Reinforcement learning with verifiable rewards improves reasoning in large language models (LLMs), but many methods still rely on large human-labeled datasets. While self-play redu…
LFPO: Likelihood-Free Policy Optimization for Masked Diffusion Models
Chenxing Wei, Jiazhen Kang, Hong Wang +8
Reinforcement Learning with Verifiable Rewards (RLVR) has achieved remarkable success in improving autoregressive models, especially in domains requiring correctness like mathemati…
Words & Weights: Streamlining Multi-Turn Interactions via Co-Adaptation
Chenxing Wei, Hong Wang, Ying He +4
Test-time policy adaptation for multi-turn interactions (T2PAM) is essential for aligning Large Language Models (LLMs) with dynamic user needs during inference time. However, exist…