{"ID":5443900,"CreatedAt":"2026-07-01T02:07:11.383974684Z","UpdatedAt":"2026-07-07T23:54:33.395952201Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.32017","arxiv_id":"2606.32017","title":"TRIAGE: Role-Typed Credit Assignment for Agentic Reinforcement Learning","abstract":"Agentic reinforcement learning requires assigning credit to environment-facing actions such as searches, clicks, edits, navigation commands, and object interactions. Standard GRPO uses the final verifier outcome as a uniform advantage over all action tokens. This outcome signal is useful but structurally incomplete: it punishes useful exploration in failed rollouts and reinforces redundant or regressive actions in successful rollouts. We propose TRIAGE, a role-typed credit assignment framework that adds a semantic role axis to outcome credit. A structured judge classifies each segment as decisive progress, useful exploration, no-progress infrastructure, or regression, and a fixed role-conditioned rule maps these labels to bounded segment-level process rewards. This keeps verifier outcomes as the source of optimization direction while correcting the two main blind spots of outcome-only credit. We further show that role-conditioned credit is the optimal segment-level correction expressible from role labels alone -- a projection of the per-segment advantage residual onto the role variable -- so that the fixed role constants reduce advantage estimation error whenever the judge is reliable, and we connect this to lower-variance policy gradients. Across ALFWorld, Search-QA, and WebShop, TRIAGE improves success rates over GRPO for two policy models and outperforms both a scalar judge-derived process reward and an outcome-supervised shared-backbone value baseline. Ablations show that the gain comes from role typing rather than merely adding dense rewards: reliable detection of regression inside successful trajectories is the dominant contributor, while exploration credit provides a consistent secondary gain; on completed ALFWorld and WebShop rollouts, TRIAGE also reduces environment-facing turns by an additional $10.4\\%$ and $14.8\\%$ relative to GRPO.","short_abstract":"Agentic reinforcement learning requires assigning credit to environment-facing actions such as searches, clicks, edits, navigation commands, and object interactions. Standard GRPO uses the final verifier outcome as a uniform advantage over all action tokens. This outcome signal is useful but structurally incomplete: it...","url_abs":"https://arxiv.org/abs/2606.32017","url_pdf":"https://arxiv.org/pdf/2606.32017v1","authors":"[\"Yuanda Xu\",\"Zhengze Zhou\",\"Hejian Sang\",\"Xiaomin Li\",\"Jiaxin Zhang\",\"Xinchen Du\",\"Zhipeng Wang\",\"Alborz Geramifard\"]","published":"2026-06-30T17:48:07Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\"]","methods":"[\"Reinforcement Learning\",\"LoRA\"]","has_code":false}