Metraipolis › archive › dc_ac10f617110c

Causal Episodic Memory for Feedback-Driven Agent Repair — arXiv:2608.05906

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.05906
License (as archived): CC0-1.0
Archived: 2026-10-25T21:27:19.026Z
SHA-256 of the archived text: 6dbbfa9453be238fd2eba0b9a8d570d8bbbbec5132eaa645537aec04cba080b7
Stable URL of this page: https://metraipolis.com/documento/dc_ac10f617110c

How to cite

Causal Episodic Memory for Feedback-Driven Agent Repair — arXiv:2608.05906 — arXiv (en), https://arxiv.org/abs/2608.05906 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ac10f617110c (Metraipolis archive dc_ac10f617110c, sha256 6dbbfa9453be238fd2eba0b9a8d570d8bbbbec5132eaa645537aec04cba080b7)

BibTeX

@misc{dcac10f617110c,
  title = {Causal Episodic Memory for Feedback-Driven Agent Repair — arXiv:2608.05906},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.05906},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ac10f617110c; sha256 6dbbfa9453be238fd2eba0b9a8d570d8bbbbec5132eaa645537aec04cba080b7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.05906. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

LLM agents that repair failures often discard successful corrections, forcing later episodes to rediscover similar solutions. We study whether finalized repair outcomes can improve subsequent Text-to-SQL episodes without parameter updates. We introduce MERIT, a training-free agent that maintains an online dual-polarity memory of oracle-verified corrections and observed unsuccessful directions. Under oracle-assisted benchmark feedback, only memories from earlier finalized episodes are eligible for retrieval. A deterministic classifier assigns a coarse failure type, which conditions a hybrid lexical-dense retriever before the frozen model generates each revision. Using Qwen2.5-7B-Instruct with identical initial predictions and repair budgets, \method{} improves execution accuracy over stateless iterative repair from \(66.34\%\) to \(69.79\%\) on Spider and from \(47.35\%\) to \(48.44\%\) on BIRD. Paired analyses provide clear evidence for the Spider gain but weaker evidence on BIRD. MERIT is not reliably separated from untyped dynamic retrieval on either benchmark, while Reflexion-style memory reaches \(51.24\%\) on BIRD at substantially higher inference cost. Ablations show that negative memory contributes modestly, the value of type conditioning and lexical-dense ranking is dataset dependent, and schema-local experience provides the most consistent benefit. These results clarify when causal cross-query memory improves repair and when broader memory representations remain preferable. Our implementation is available here:

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-07 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.05906 — 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 2026-10-25T21:24:38.217Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).