4 papers · 1 filter
Uncovering and Mitigating Aggregation-Induced Reward Hacking in Multi-Reward Reinforcement Learning
Yu Yuan, Yaoyou Fan, Lili Zhao +5
Reinforcement learning fine-tuning of large language models increasingly adopts multiple reward dimensions, including verifiable rules, task-specific evaluators, and learned reward…
Rethinking Continual Experience Internalization for Self-Evolving LLM Agents
Jingwen Chen, Wenkai Yang, Shengda Fan +7
Experience internalization converts contextual experience from past interactions into reusable parametric capability, offering a promising path toward continual learning in large l…
Attention-MoA: Enhancing Mixture-of-Agents via Inter-Agent Semantic Attention and Deep Residual Synthesis
Jianyu Wen, Yang Wei, Xiongxi Yu +2
As the development of Large Language Models (LLMs) shifts from parameter scaling to inference-time collaboration, the Mixture-of-Agents (MoA) framework has emerged as a general par…
Rectify Evaluation Preference: Improving LLMs' Critique on Math Reasoning via Perplexity-aware Reinforcement Learning
Changyuan Tian, Zhicong Lu, Shuang Qian +8
To improve Multi-step Mathematical Reasoning (MsMR) of Large Language Models (LLMs), it is crucial to obtain scalable supervision from the corpus by automatically critiquing mistak…