智能体
arxiv.org ·
@Arlindo L. Oliveira
双过程语言 Agent 的认知扩展：交互环境中的记忆与自我反思
针对语言 Agent 在交互环境中长程状态跟踪、动作执行与失败恢复脆弱的问题，论文在双过程 Agent SwiftSage（快速动作提议器加较慢规划器）上引入两个模块化扩展：自适应记忆模块 AMM 负责显著性门控的情景存储与触发式检索，自我反思模块 SRM 负责有界的执行期校验与纠正干预。两者以特性开关形式实现于同一执行底座，便于在 ScienceWorld 上做受控消融。四组配置对比中，完整系统取得最佳平均最终得分 64.62、成功率 43.17%、成功步效率 19.33 步，SRM 是单独贡献最强的模块，结果指向执行期控制是主要瓶颈。
AI推荐理由 论文在双过程 Agent SwiftSage 上增加自适应记忆模块（AMM）与自我反思模块（SRM），并在 ScienceWorld 上做四组消融，报告完整系统取得最佳平均最终得分 64.62、成功率 43.17%、成功步效率 19.33 步，SRM 为最强单模块贡献。实验设置与数值明确，对交互式 Agent 的执行期控制有直接参考价值；但仅在单一基准上验证，结论外推需谨慎。
72
正文
Computer Science > Artificial Intelligence
arXiv:2609.19128v1 (cs)
[Submitted on 16 Sep 2026]
Title:Cognitive Extensions for Dual-Process Language Agents: Memory and Self-Reflection in Interactive Environments
Authors:João Meneses dos Santos, Arlindo L. Oliveira
View a PDF of the paper titled Cognitive Extensions for Dual-Process Language Agents: Memory and Self-Reflection in Interactive Environments, by Jo\~ao Meneses dos Santos and Arlindo L. Oliveira
View PDF
HTML (experimental)
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.
Comments:
Subjects:
Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Multiagent Systems (cs.MA)
Cite as:
arXiv:2609.19128 [cs.AI]
(or
arXiv:2609.19128v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2609.19128
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Joao Miguel Meneses Dos Santos [view email]
[v1]
Wed, 16 Sep 2026 17:50:42 UTC (260 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Cognitive Extensions for Dual-Process Language Agents: Memory and Self-Reflection in Interactive Environments, by Jo\~ao Meneses dos Santos and Arlindo L. Oliveira
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.AI
new
|
recent
| 2026-09
Change to browse by:
cs
cs.LG
cs.MA
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)