activity
20232026
most citedCMMaTH: A Chinese Multi-modal Math Skill Evaluation Benchmark for Foundation Models

2 citations · 3 across the 12 of their papers we have counts for

collaborators

14 papers

cs.LG2026

T1: Terminal Agent Reinforcement Learning for Long-Horizon Tasks

Junyao Yang, Yucheng Shi, Zhongzhi Li +4

Agent usage is shifting toward long-horizon tasks such as coding and scientific discovery, among which terminal tasks are especially important. We introduce T1, a Mixture-of-Expert…

cs.AI2026

Recursive Synthesis for Long-Horizon Terminal Tasks

Zhongzhi Li, Yucheng Shi, Zongxia Li +8

High-quality long-horizon training data for terminal agents is expensive to produce, often costing hundreds to thousands of dollars per task, because each task must keep the instru…

cs.LG2026

Stale but Stable: Staleness-Adaptive Trust Regions for Stabilizing Asynchronous Reinforcement Learning

Junyao Yang, Yucheng Shi, Zongxia Li +6

Asynchronous reinforcement learning improves throughput by decoupling rollout generation from optimization, but the resulting staleness is an inevitable byproduct, compounded joint…

cs.AI2026

Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable

Ruhan Wang, Yucheng Shi, Zongxia Li +7

The capability of a modern AI agent depends not only on its foundation model but also on its harness, which constructs prompts, manages state, invokes tools, and coordinates execut…

cs.AI2026

Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading

Zongxia Li, Zhongzhi Li, Yucheng Shi +10

AI agents have become capable of autonomously completing short, well-specified tasks. However, existing terminal benchmarks largely focus on simple problems that finish within minu…

cs.CL2026

Less is Enough: Synthesizing Diverse Data in LLM Feature Space with Sparse Autoencoders

Zhongzhi Li, Xuansheng Wu, Yijiang Li +2

The diversity of post-training data is critical for effective downstream performance in large language models (LLMs). Many existing approaches to constructing post-training data qu…