发表机构
Instituto Superior Técnico, Universidade de Lisboa; INESC-ID（里斯本大学高等技术学院; INESC-ID研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究通过为双过程语言智能体SwiftSage添加自适应记忆模块和自我反思模块，在ScienceWorld环境中显著提升了任务成功率，并发现执行时间控制是主要瓶颈。
AI 中文摘要
语言智能体在交互环境中仍然脆弱，在此类环境中，成功需要长程状态跟踪、有效的动作执行以及从失败步骤中恢复的能力。我们扩展了SwiftSage——一种结合快速动作提议器与较慢规划器的双过程智能体——通过两种模块化认知扩展：自适应记忆模块（AMM），用于显著性门控的情景存储和触发驱动检索；以及自我反思模块（SRM），用于有界执行时间验证和纠正性干预。两个模块均作为特征标记扩展实现于同一执行基底之上，从而能够在ScienceWorld上进行受控消融实验。在四种配置中——基线、基线+AMM、基线+SRM以及完整系统——完整系统取得了最佳平均最终得分（64.62）、成功率（43.17%）和成功步骤效率（19.33步），而SRM是最强的独立贡献者。结果表明，在此设置中，执行时间控制是主导瓶颈，而一旦运行时循环稳定，情景记忆则变得最为有用。
英文摘要
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.
Comments13 pages, 1 figure
