activity
20242026
collaborators

5 papers

cs.LG2026

Stronger-MAS: Multi-Agent Reinforcement Learning for Collaborative LLMs

Yujie Zhao, Lanxiang Hu, Yang Wang +4

Multi-agent systems (MAS) and reinforcement learning (RL) are widely used to enhance the agentic capabilities of large language models (LLMs). MAS improves task performance through…

cs.AI2025

Towards Interpretable and Inference-Optimal COT Reasoning with Sparse Autoencoder-Guided Generation

Daniel Zhao, Abhilash Shankarampeta, Lanxiang Hu +2

We propose a novel method that leverages sparse autoencoders (SAEs) and clustering techniques to analyze the internal token representations of large language models (LLMs) and guid…

cs.AI2025

General Modular Harness for LLM Agents in Multi-Turn Gaming Environments

Yuxuan Zhang, Haoyang Yu, Lanxiang Hu +2

We introduce a modular harness design for LLM agents that composes of perception, memory, and reasoning components, enabling a single LLM or VLM backbone to tackle a wide spectrum…

cs.CL2025

ReFoRCE: A Text-to-SQL Agent with Self-Refinement, Consensus Enforcement, and Column Exploration

Minghang Deng, Ashwin Ramachandran, Canwen Xu +4

We present ReFoRCE, a Text-to-SQL agent that tops the Spider 2.0 leaderboard--a challenging benchmark reflecting complex, real-world Text-to-SQL scenarios. While Text-to-SQL system…

cs.LG2024

TrimLLM: Progressive Layer Dropping for Domain-Specific LLMs

Lanxiang Hu, Tajana Rosing, Hao Zhang

Specializing large language models (LLMs) for local deployment in domain-specific use cases is necessary for strong performance while meeting latency and privacy constraints. Howev…