From the 2 of 10 linked papers with an AI index.
10 papers
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…
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…
Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable
Ruhan Wang, Yucheng Shi, Zongxia Li +7
The paper presents the Harness Handbook, a tool that automatically creates a behavior‑centric view of AI agent harness code using static analysis and LLM assistance, enabling devel…
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
The paper presents Long-Horizon-Terminal-Bench, a benchmark of 46 extended tasks with fine-grained intermediate rewards to evaluate AI agents' long-horizon planning and debugging a…
FERA: Uncertainty-Aware Federated Reasoning for Large Language Models
Ruhan Wang, Chengkai Huang, Zhiyong Wang +6
Large language models (LLMs) exhibit strong reasoning capabilities when guided by high-quality demonstrations, yet such data is often distributed across organizations that cannot c…
Return Augmented Decision Transformer for Off-Dynamics Reinforcement Learning
Ruhan Wang, Yu Yang, Zhishuai Liu +2
We study offline off-dynamics reinforcement learning (RL) to utilize data from an easily accessible source domain to enhance policy learning in a target domain with limited data. O…