Showing cs.LGShow all
3 papers · 1 filter
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.LG2026
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…
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…