8 papers
Long-Horizon-Terminal-Bench 2.0: Automating Diverse Task Construction and Measuring Sustained Agent Progress
Zongxia Li, Zhongzhi Li, Yucheng Shi +14
Long-horizon terminal benchmarks measure whether an agent can sustain progress through extended workflows with process rewards, not only whether its final state passes a binary che…
Self-Supervised Scaling of Terminal Environments for Scientific Domains
Zhongzhi Li, Yucheng Shi, Zongxia Li +8
Terminal agents are increasingly deployed beyond software engineering in science and other specialized domains. Constructing training environments requires executable reference beh…
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…
FlowBalance: Verifier-Grounded Self-Improvement from On-Policy Reasoning Experience
Zixun Huang, Kishan Panaganti, Haitao Mi +1
A reasoning model can improve from its own on-policy experience, but this inner loop is fragile: terminal verifiers provide reliable yet sparse supervision, while dense same-model…
UI-Mate: Advancing Open-Weight Foundation GUI Agents with In-Context Demonstrations
Zihan Ding, Longxu Dou, Qi Gao +26
Foundation GUI agents can automate complex digital tasks, but deployment is hindered by scarce and biased training data, ambiguous prompts, and unreliable execution. Routine workfl…
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…
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 +12
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…