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-enhanced tool-integrated agents.
Abstract
Self-evolving methods reduce the need for human-annotated trajectories by allowing tool-using agents to generate their own training data. Yet existing methods typically separate trajectory generation from evaluation, relying on static verifiers that cannot adapt to emerging failure modes or self-consistency signals that may reinforce errors shared across trajectories. Jointly adapting planning, execution, and evaluation offers a promising alternative, but introduces a fundamental coordination challenge: each component continuously changes the data or feedback used to train the others. We address this challenge with \textbf{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. We design role-specific rewards that coordinate the three players toward a shared learning objective under GRPO. Across two model backbones and twelve reasoning benchmarks, UnifiedPlayers outperforms the strongest prior baseline by at least 3.5\% on mathematical reasoning and 3.9\% on general reasoning tasks. Moreover, the learned verifier achieves 84.2\% adversarial detection accuracy, while its reward signal exhibits 2.03$\times$ higher per-question variance than a self-consistency baseline, providing more discriminative verifications. These results highlight cooperation among specialized players as a promising path toward self-enhanced tool-integrated agents.
This paper introduces HarnessEvolve, a self-evolving framework that learns from reference trajectories to achieve reliable agent self-evolution, and overcomes credit assignment failure by generating reference trajectories and aligning failed executions against them to extract error signals.
Wen Jiang, Ming-Min Chu, Yiding Tian et al.· 14 citations
Language model agents are increasingly deployed in open-world tool environments, which require balancing exploring unknown capabilities and exploiting known ones. Existing methods face a performance-efficiency tradeoff: they either rigidly decouple exploration and execution or interleave them without coordination. We a...
Shengbin Yue, Hongru Wang, Siyuan Wang et al.· arXiv.org· 1 citation
This work introduces StructReward, a compute-efficient framework that provides dense reinforcement signals through structured step-level reward alignment and substantially reduces the computational overhead of multimodal reinforcement learning.
River, a simple training recipe that improves reward quality by filtering low-quality environments and augmenting outcome rewards with process-level behavior regularization is proposed, which achieves the best performance among evaluated open-source RL-trained 8B models across four terminal-agent benchmarks.
Yi-Fan Yao, Bo Pang, Xuan-Phi Nguyen et al.· 2 citations
Executable environments enable LLM agents to learn from the consequences of their actions. For embodied agents, those consequences extend beyond whether the current task succeeds: completing a delivery can consume the time, energy, or money needed for later work. Learning to plan therefore requires environments that pr...
SPADE (Self-Play in Adaptive Synthetic Executable Executable Environments), a self-play RL framework in which a single LLM plays two roles: an Environment Designer that writes complete, long-horizon training environments as executable code with an OpenAI Gym-style reset()/step() interface, and a Reasoning Agent that le...
Bo Liu, Simon Yu, Yiding Jiang et al.· 7 citations