Metraipolis › archive › dc_54b4765907bc

CHIME: Credit-Aware Hierarchical Memory Evolution for Long-Horizon Agentic Planning — arXiv:2609.02074

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.02074
License (as archived)
CC0-1.0
Archived
2026-10-17T03:25:54.403Z
SHA-256 of the archived text
e44443b7815f9c91d3b081c1d56a9f5d04c8c12374854d8a3ce437d06d65bd78
Stable URL of this page
https://metraipolis.com/documento/dc_54b4765907bc

How to cite

CHIME: Credit-Aware Hierarchical Memory Evolution for Long-Horizon Agentic Planning — arXiv:2609.02074 — arXiv (en), https://arxiv.org/abs/2609.02074 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_54b4765907bc (Metraipolis archive dc_54b4765907bc, sha256 e44443b7815f9c91d3b081c1d56a9f5d04c8c12374854d8a3ce437d06d65bd78)
BibTeX
@misc{dc54b4765907bc,
  title = {CHIME: Credit-Aware Hierarchical Memory Evolution for Long-Horizon Agentic Planning — arXiv:2609.02074},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.02074},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_54b4765907bc; sha256 e44443b7815f9c91d3b081c1d56a9f5d04c8c12374854d8a3ce437d06d65bd78},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.02074. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Planning is a central capability that enables agents to decompose complex long-horizon tasks into manageable steps. Test-time search and training-based methods improve planning but incur high inference costs or require expensive training data. Self-evolving memory instead accumulates reusable experience from agent interaction outcomes into an external memory bank, so planning capability keeps improving at inference time without parameter updates. However, existing self-evolving memory methods share an inherent credit assignment problem: they rely on final task outcomes as feedback, but such outcomes conflate plan quality with execution errors and environmental factors, so the accumulated planning experience is often biased and noisy. To address this problem, we propose Credit-Aware Hierarchical Memory Evolution (CHIME), a self-evolving memory framework that maintains a separate planning bank and execution bank and follows an attribute-before-memorize principle: CHIME first attributes each task outcome to the plan, the execution, both, or neither, and then updates only the corresponding memory bank. Extensive experiments on four long-horizon agent benchmarks show that CHIME consistently outperforms state-of-the-art training-based and self-evolving memory baselines. Further analyses reveal several interesting findings. For example, CHIME accumulates effective memory with far fewer items. In addition, the learned memory values faithfully reflect downstream utility: high-quality planning memories are more valuable than execution memories. Finally, the accumulated memory effectively transfers across backbone models. Code will be released at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-03 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.02074 — 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 2026-10-17T03:13:12.417Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).