collaborators

20 papers

cs.AI2026

MANTA: Multi-Agent Network Topology Adaptation for Self-Evolving Multi-Agent Systems

Mao-xun Huang, Jerry Wang, Yi-Cheng Lai +3

The paper presents MANTA, a framework that lets large language model‑driven multi‑agent systems dynamically adjust their communication topology during inference, updating roles, li…

cs.AI2026

FIRE-Bench: Evaluating AI Agents on the Rediscovery of Scientific Insights

Zhen Wang, Fan Bai, Zhongyan Luo +9

Autonomous agents powered by large language models (LLMs) promise to accelerate scientific discovery end-to-end, but rigorously evaluating their capacity for verifiable discovery r…

cs.LG2026

HARP: Efficient Data Selection for Finetuning Large Language Models

Ning Wang, Zhengxin Zhang, Maosen Tang +3

Finetuning data selection requires balancing two competing goals: selecting examples that improve the downstream objective, and doing so without repeatedly finetuning models. Train…

cs.CL2026

Token-weighted Direct Preference Optimization with Attention

Chengyu Huang, Zhuohang Li, Sheng-Yen Chou +1

Direct Preference Optimization (DPO) aligns Large Language Models with human preferences without the need for a separate reward model. However, DPO treats all tokens in responses e…

cs.CL2026

Knowing but Not Showing: LLMs Recognize Ambiguity but Rarely Ask Clarifying Questions

Jinyan Su, Claire Cardie

User queries are often underspecified and may admit multiple valid interpretations. Rather than silently making assumptions about the user's intent, a helpful assistant should surf…

cs.AI2026

How Far Are We From True Auto-Research?

Zhengxin Zhang, Ning Wang, Sainyam Galhotra +1

Recent auto-research systems can produce complete papers, but feasibility is not the same as quality, and the field still lacks a systematic study of how good agent-generated paper…