9 papers
AgentPanel: Toward a New Paradigm for Human--AI Collaboration in Exploring Scientific Questions
Zhiyao Cui, Qianyi Wang, Haoyang Yan +26
Identifying promising scientific ideas remains an important challenge in research practice. Researchers commonly rely on small-group discussions or one-to-one interactions with a s…
Disentangling Intent from Role: Adversarial Self-Play for Persona-Invariant Safety Alignment
Jiajia Li, Xiaoyu Wen, Zhongtian Ma +3
The growing capabilities of large language models (LLMs) have driven their widespread deployment across diverse domains, even in potentially high-risk scenarios. Despite advances i…
Adaptive Theory of Mind for LLM-based Multi-Agent Coordination
Chunjiang Mu, Ya Zeng, Qiaosheng Zhang +6
Theory of Mind (ToM) refers to the ability to reason about others' mental states, and higher-order ToM involves considering that others also possess their own ToM. Equipping large…
LLMRouterBench: A Massive Benchmark and Unified Framework for LLM Routing
Hao Li, Yiqun Zhang, Zhaoyan Guo +9
Large language model (LLM) routing assigns each query to the most suitable model from an ensemble. We introduce LLMRouterBench, a large-scale benchmark and unified framework for LL…
When Human Preferences Flip: An Instance-Dependent Robust Loss for RLHF
Yifan Xu, Xichen Ye, Yifan Chen +1
Quality of datasets plays an important role in large language model (LLM) alignment. In collecting human feedback, however, preference flipping is ubiquitous and causes corruption…
ICL-Router: In-Context Learned Model Representations for LLM Routing
Chenxu Wang, Hao Li, Yiqun Zhang +6
Large language models (LLMs) often exhibit complementary strengths. Model routing harnesses these strengths by dynamically directing each query to the most suitable model, given a…
The Path of Self-Evolving Large Language Models: Achieving Data-Efficient Learning via Intrinsic Feedback
Hangfan Zhang, Siyuan Xu, Zhimeng Guo +8
Reinforcement learning (RL) has demonstrated potential in enhancing the reasoning capabilities of large language models (LLMs), but such training typically demands substantial effo…
Do We Truly Need So Many Samples? Multi-LLM Repeated Sampling Efficiently Scales Test-Time Compute
Jianhao Chen, Zishuo Xun, Bocheng Zhou +8
This paper presents a simple, effective, and cost-efficient strategy to improve LLM performance by scaling test-time compute. Our strategy builds upon the repeated-sampling-then-vo…
Sample-Efficient Reinforcement Learning from Human Feedback via Information-Directed Sampling
Han Qi, Haochen Yang, Qiaosheng Zhang +1
We study the problem of reinforcement learning from human feedback (RLHF), a critical problem in training large language models, from a theoretical perspective. Our main contributi…