7 papers
Collaborative Personalized Preference Alignment for LLMs under Data Deficiency
Liyan Yang, Yige Yuan, Zhiqin Yang
Real-world users often exhibit highly heterogeneous preferences over multiple objectives for LLM responses. A lightweight aligner can tailor these responses to individual preferenc…
Rethinking the Evaluation of Harness Evolution for Agents
Yike Wang, Huaisheng Zhu, Zhengyu Hu +8
Harness evolution is an iterative search procedure that repeatedly evaluates and revises candidate harnesses used for LLM agents using task feedback. We revisit the evaluation of s…
Co-Harness: Co-Evolving Harnesses and Model Weights for LLM Agents
Zhengyu Chen, Teng Xiao, Huaisheng Zhu +3
Post-training agents for automated AI research requires optimizing not only model parameters, but also the runtime harness that shapes how research trajectories are generated, eval…
Meta-Reinforcement Learning with Self-Reflection for Agentic Search
Teng Xiao, Yige Yuan, Hamish Ivison +6
This paper introduces MR-Search, an in-context meta reinforcement learning (RL) formulation for agentic search with self-reflection. Instead of optimizing a policy within a single…
Simple Denoising Diffusion Language Models
Huaisheng Zhu, Zhengyu Chen, Shijie Zhou +8
Recent Uniform State Diffusion Models (USDMs), initialized from a uniform prior, offer the promise of fast text generation due to their inherent self-correction ability compared to…
On a Connection Between Imitation Learning and RLHF
Teng Xiao, Yige Yuan, Mingxiao Li +2
This work studies the alignment of large language models with preference data from an imitation learning perspective. We establish a close theoretical connection between reinforcem…
SimPER: A Minimalist Approach to Preference Alignment without Hyperparameters
Teng Xiao, Yige Yuan, Zhengyu Chen +4
Existing preference optimization objectives for language model alignment require additional hyperparameters that must be extensively tuned to achieve optimal performance, increasin…