SwiftSage 模型新增记忆与自省模块，提升交互环境表现
Cognitive Extensions for Dual-Process Language Agents: Memory and Self-Reflection in Interactive Environments
这是 SwiftSage 模型的一个技术升级，增加了记忆和自省功能，可能对需要长期状态追踪和恢复能力的交互式任务有帮助。
研究团队扩展了 SwiftSage 双过程语言代理，通过自适应记忆模块（AMM）实现 salience-gated 的存储与检索，以及自省模块（SRM）进行执行时间验证和纠正。
在 ScienceWorld 基准上，完整系统（AMM+SRM）的平均最终分数达到 64.62，成功率为 43.
17%，而单独的自省模块（SRM）是主要贡献者。
Cognitive Extensions for Dual-Process Language Agents: Memory and Self-Reflection in Interactive Environments
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.
本条情报归属 AITOP「模型」核心栏目，重点聚焦北美前沿实验室与硅谷科技巨头。在跨区域产业观察坐标中，该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」「中美大模型技术代差与商业化对照」研究主线，反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括：SwiftSage、双过程代理、记忆模块、自省模块，读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。
信源核验说明：本文原始线索采编自「arXiv cs.AI」（@João Meneses dos Santos, Arlindo L. Oliveira），经 AITOP 多维评分管线结构化提炼。
