{"ID":22952804,"CreatedAt":"2026-09-17T02:12:05.498442134Z","UpdatedAt":"2026-09-20T18:11:56.143995915Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2609.19128","arxiv_id":"2609.19128","title":"Cognitive Extensions for Dual-Process Language Agents: Memory and Self-Reflection in Interactive Environments","abstract":"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.","short_abstract":"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 Adaptiv...","url_abs":"https://arxiv.org/abs/2609.19128","url_pdf":"https://arxiv.org/pdf/2609.19128v1","authors":"[\"João Meneses dos Santos\",\"Arlindo L. Oliveira\"]","published":"2026-09-16T17:50:42Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.LG\",\"cs.MA\"]","methods":"[]","has_code":false}