long-horizon agents
2 stories tagged “long-horizon agents”.
-
Moving Beyond Timestamps: On-Policy Distillation Aligned with Decisions for Long-Horizon Agents
AlignOPSD moves distillation from timestamps to functional decision spans, using credit assignment to improve …
-
QwenGyre: A Dynamically Scalable Reinforcement Learning Framework for Training xLong-Horizon Agents
QwenGyre boosts long-horizon online RL with elastic GPU reallocation and trajectory deduplication, lifting NL2…