activity
20242026
collaborators

7 papers

cs.AI2026

DarkForest: Less Talk, Higher Accuracy for Multi-Agent LLMs

Yi Li, Songtao Wei, Dongming Jiang +3

Multi-agent LLM systems improve reasoning by combining outputs from multiple agents, but interaction-heavy methods can introduce error propagation and high communication overhead.…

cs.LG2026

LEAD: Length-Efficient Adaptive and Dynamic Reasoning for Large Language Models

Songtao Wei, Yi Li, Zhikai Li +7

Large reasoning models, such as OpenAI o1 and DeepSeek-R1, tend to become increasingly verbose as their reasoning capabilities improve. These inflated Chain-of-Thought (CoT) trajec…

cs.LG2026

Reinforcement Learning with LLM-Guided Action Spaces for Synthesizable Lead Optimization

Tao Li, Kaiyuan Hou, Tuan Vinh +3

Lead optimization in drug discovery requires improving therapeutic properties while ensuring that molecular modifications correspond to feasible synthetic routes. Existing approach…

cs.LG2026

CoSA: Compressed Sensing-Based Adaptation of Large Language Models

Songtao Wei, Yi Li, Bohan Zhang +6

Parameter-Efficient Fine-Tuning (PEFT) has emerged as a practical paradigm for adapting large language models (LLMs) without updating all parameters. Most existing approaches, such…

cs.LG2025

Improving Protein Sequence Design through Designability Preference Optimization

Fanglei Xue, Andrew Kubaney, Zhichun Guo +4

Protein sequence design methods have demonstrated strong performance in sequence generation for de novo protein design. However, as the training objective was sequence recovery, it…

cs.LG2024

YOSO: You-Only-Sample-Once via Compressed Sensing for Graph Neural Network Training

Yi Li, Zhichun Guo, Guanpeng Li +1

Graph neural networks (GNNs) have become essential tools for analyzing non-Euclidean data across various domains. During training stage, sampling plays an important role in reducin…