Metraipolis › archive › dc_02da6bfcdb84

Agentic Reinforcement Learning with Self-Distilled Reward Shaping — arXiv:2608.03223

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.03223
License (as archived)
CC0-1.0
Archived
2026-10-31T12:18:41.154Z
SHA-256 of the archived text
43110810f989a8efa96bb94033d16b399eaba7786c61b58df24f1081a3983418
Stable URL of this page
https://metraipolis.com/documento/dc_02da6bfcdb84

How to cite

Agentic Reinforcement Learning with Self-Distilled Reward Shaping — arXiv:2608.03223 — arXiv (en), https://arxiv.org/abs/2608.03223 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_02da6bfcdb84 (Metraipolis archive dc_02da6bfcdb84, sha256 43110810f989a8efa96bb94033d16b399eaba7786c61b58df24f1081a3983418)
BibTeX
@misc{dc02da6bfcdb84,
  title = {Agentic Reinforcement Learning with Self-Distilled Reward Shaping — arXiv:2608.03223},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.03223},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_02da6bfcdb84; sha256 43110810f989a8efa96bb94033d16b399eaba7786c61b58df24f1081a3983418},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03223. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Agentic reinforcement learning enables LLM agents to learn through interaction, but sparse trajectory-level rewards reveal success without identifying which intermediate decisions deserve credit. Training-only privileged skills can provide denser supervision by allowing the same frozen policy snapshot to rescore fixed tokens from skill-free trajectories while conditioned on task-matched procedural skills. Existing methods, however, do not jointly calibrate teacher scores across interaction steps, relate teacher confidence to realized returns, and integrate the resulting signal into native reward-to-advantage construction. We introduce Agentic Reinforcement Learning with Self-Distilled Reward Shaping (ADRS), a framework for constructing return-associated token-level credit for multi-turn language agents. ADRS centers and normalizes privileged token scores within each step, modulates them with a return-associated Teacher Value Advantage (TVA) gate based on within-group confidence--return association, and incorporates the gated token signal into native RL credit construction. Together, these components determine what the teacher prefers, when that preference is return-relevant, and how it enters the native reinforcement-learning credit path, while keeping rollouts and inference skill-free. Finally, experiments across three interactive benchmarks show that ADRS consistently improves performance on long-horizon tasks, with gains persisting across RL backbones, reduced-data settings, unseen tasks, and extended training. For anonymous review, our code is available at the following the link: this https URL

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-05 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.03223 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-31T12:05:53.018Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).