{"paper":{"title":"Keep Policy Gradient in Charge: Sibling-Guided Credit Distillation for Long-Horizon Tool-Use Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Jianhong Xin, Juan Pablo De la Cruz Weinstein, Tianyu Ding","submitted_at":"2026-06-10T19:53:20Z","abstract_excerpt":"Long-horizon tool-use reinforcement learning can learn from outcome verification, but its\n  trajectory-level advantage is broadcast across many reasoning, API, and answer tokens.\n  Self-distillation promises a denser signal by reusing a policy's own rollouts or a privileged\n  teacher. We show, however, that direct token-level self-distillation can silently destroy tool use:\n  it rehearses teacher behavior without knowing which actions the verifier rewards, so useful skills\n  and harmful shortcuts are amplified together. We introduce Sibling-Guided Credit Distillation\n  (SGCD), which uses disti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.12634","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.12634/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}