Metraipolis › archive › dc_bcaa15d79f5e
Cognitive Extensions for Dual-Process Language Agents: Memory and Self-Reflection in Interactive Environments — arXiv:2609.19128
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.19128
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T15:08:14.662Z
- SHA-256 of the archived text
cc3408b46ac18548757d524ae4321fdafa5a40f0656d96d10a1527a7369cde3c- Stable URL of this page
https://metraipolis.com/documento/dc_bcaa15d79f5e
How to cite
Cognitive Extensions for Dual-Process Language Agents: Memory and Self-Reflection in Interactive Environments — arXiv:2609.19128 — arXiv (en), https://arxiv.org/abs/2609.19128 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bcaa15d79f5e (Metraipolis archive dc_bcaa15d79f5e, sha256 cc3408b46ac18548757d524ae4321fdafa5a40f0656d96d10a1527a7369cde3c)
BibTeX
@misc{dcbcaa15d79f5e,
title = {Cognitive Extensions for Dual-Process Language Agents: Memory and Self-Reflection in Interactive Environments — arXiv:2609.19128},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.19128},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bcaa15d79f5e; sha256 cc3408b46ac18548757d524ae4321fdafa5a40f0656d96d10a1527a7369cde3c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.19128. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Language agents remain brittle in interactive environments, where success requires long-horizon state tracking, valid action execution, and recovery from failed steps. We extend SwiftSage, a dual-process agent that combines a fast action proposer with a slower planner, using two modular cognitive extensions: an Adaptive Memory Module (AMM) for salience-gated episodic storage and trigger-driven retrieval, and a Self-Reflection Module (SRM) for bounded execution-time validation and corrective intervention. Both modules are implemented as feature-flagged extensions over the same execution substrate, enabling controlled ablations on ScienceWorld. Across four configurations---baseline, baseline+AMM, baseline+SRM, and the full system---the full system achieves the best mean final score (64.62), success rate (43.17%), and successful-step efficiency (19.33 steps), while SRM is the strongest standalone contributor. The results suggest that execution-time control is the dominant bottleneck in this setting, while episodic memory becomes most useful once the runtime loop is stabilized. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-17 in cs.LG). Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG); Multiagent Systems (cs.MA). Pagina del lavoro: https://arxiv.org/abs/2609.19128 — 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 2026-10-15T14:08:19.297Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).