collaborators

22 papers

cs.LG2026

Weak-to-Strong Generalization via Direct On-Policy Distillation

Shiyuan Feng, Huan-ang Gao, Haohan Chi +7

Reinforcement learning with verifiable rewards (RLVR) is a powerful recipe for improving language-model reasoning, but it is expensive to repeat on every new strong model because t…

cs.CL2026

NatureBench: Can Coding Agents Match the Published SOTA of Nature-Family Papers?

Yuru Wang, Lejun Cheng, Yuxin Zuo +14

We introduce NatureBench, a cross-discipline benchmark of 90 tasks distilled from peer-reviewed Nature-family publications, designed to evaluate whether AI coding agents can move b…

cs.CL2026

Scalable Behaviour Cloning on Browser Using via Skill Distillation

Kaisen Yang, Zheng Jiang, Yuzhao Peng +11

Internet users collectively perform an enormous range of skilled work through web browsers, from software development and document editing to search, forms, and enterprise workflow…

cs.AI2026

CostBench: Evaluating Multi-Turn Cost-Optimal Planning and Adaptation in Dynamic Environments for LLM Tool-Use Agents

Jiayu Liu, Cheng Qian, Zhaochen Su +4

Current evaluations of Large Language Model (LLM) agents primarily emphasize task completion, often overlooking resource efficiency and adaptability. This neglects a crucial capabi…

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…