Self-evolving tool-integrated agents learn from tasks and feedback generated within their own training loop. A Curriculum Agent generates tasks, while an Executor Agent learns from self-consistency signals through reinforcement learning. However, relying solely on the current Executor for feedback has two limitations:...
In cooperative Multi-Agent Reinforcement Learning (MARL), agents are often trained under concurrent participation, while in many tasks some agents act earlier and leave task-relevant information that becomes useful to agents participating later. We study this setting as staggered participation (SP), which introduces a...
Jiang-Lin Qiao, Si-Yi Hu, T. Nguyen et al.· 0 citations
Decoupled Credit Self-Distillation is introduced, which theoretically decouples credit direction and magnitude into two reliable signals and uses them to calibrate privileged teacher supervision, enabling step-to-token credit assignment for policy optimization.
Yu-Gu Li, Ze-Hong Cao, Pei-Zhen Li et al.· 0 citations
UnifiedPlayers, a cooperative framework comprising a Planning Player that generates tasks, an Execution Player that produces multi-turn trajectories with Python tool calls, and an Evaluation Player that constructs executable verifiers, highlights cooperation among specialized players as a promising path toward self-enh...
This work proposes Reverse-Turn Policy Optimization (RTPO), which organizes multi-turn rollouts as sparse reverse trees and performs turn-level policy updates in temporal reverse order, aligning each decision with its downstream continuation.
Yu-Gu Li, Ze-Hong Cao, Jiang-Lin Qiao et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.