activity
20232026
most citedOn the Safety of Open-Sourced Large Language Models: Does Alignment Really Prevent Them From Being Misused?

5 citations · 12 across the 14 of their papers we have counts for

collaborators

14 papers

cs.AI2026

Rethinking the Evaluation of Harness Evolution for Agents

Yike Wang, Huaisheng Zhu, Zhengyu Hu +7

We revisit the evaluation of automatic harness evolution for LLM agents. Existing harness evolution methods use unit test cases to search for harness configurations and then report…

cs.AI2026

Beyond Final Scores: A Systematic Evaluation of Agents for Long-Horizon AI Research and Development

Yiwei Li, Wanli Yang, Hexiang Tan +10

Autonomous agents are increasingly capable of improving models, systems, and other technical artifacts through long-horizon experimentation. To understand the current state of this…

cs.AI2026

Distilling Temporal Search and Reasoning: Evolving LLMs for Future Prediction via Harness-Assisted Efficient Data Synthesis

Wanxu Cai, Zhengyu Chen, Huaisheng Zhu +3

Future event prediction carries broad social impact yet remains challenging. SOTA approaches augment LLMs with external agent frameworks whose predictive capability vanishes once t…

cs.AI2026

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…

cs.LG2026

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…

cs.CL2025

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…