collaborators

9 papers

cs.AI2026

@skills: Attention is all you have

Li Yin, Zhi Li, Zhan Shi +4

There are 56,804 public agent skills today, and teams write many more privately. The dominant delivery model is installation: once installed, a skill's description remains in the s…

physics.chem-ph2026

Diffusion and Solvation Dynamics of Ions in Water: Beyond the Brownian Approximation

Ian C. Bourg, Minh Thê Hoang Ngoc, Thomas R. Underwood +1

The coupled dynamics of ions and water molecules in their first hydration shell impact a variety of processes including ion diffusion, selective ion transport in water-filled nanop…

cs.AI2026

A-Evolve-Training: Autonomous Post-Training of a 30B Model

Zhan Shi, Bing He, Yisi Sang +2

Post-training a frontier model is normally weeks of human work: proposing data and recipe changes, launching runs, reading evals, deciding what to keep. We report an autonomous sys…

cs.LG2026

Adaptive Auto-Harness: Sustained Self-Improvement for Agentic System Deployment on Open-Ended Task Streams

Zewen Liu, Zhan Shi, Yisi Sang +7

Auto-harness systems such as A-Evolve, GEPA, and Meta-Harness improve LLM agents by optimizing prompts, skills, tools, memories, and supporting infrastructure from execution feedba…

cs.AI2026

Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents

Minhua Lin, Juncheng Wu, Zijun Wang +14

LLM agents are increasingly deployed as systems built around editable external harnesses, including prompts, skills, memories and tools, that shape task execution without changing…

cs.AI2026

Controllable and Verifiable Tool-Use Data Synthesis for Agentic Reinforcement Learning

Siyuan Xu, Shiyang Li, Xin Liu +9

Existing synthetic tool-use corpora are primarily designed for offline supervised fine-tuning, yet reinforcement learning (RL) requires executable environments that support reward-…