AI Agent

Inferring agent objectives at different scales of a complex adaptive system

Dieter Hendricks, Adam Cobb, Richard Everett, Jonathan Downing, Stephen J. Roberts

专题命中 记忆与上下文管理 ：agent(title,abstract)

Comments 6 pages, 3 figures, NIPS 2017 Workshop on Learning in the Presence of Strategic Behaviour (MLStrat)

Empirical analysis and agent-based modeling of Lithuanian parliamentary elections

A. Kononovicius

专题命中 记忆与上下文管理 ：agent(title,abstract)

Comments 19 pages, 11 figures

Journal ref Complexity 2017: 7354642

Parallelization Strategies for Spatial Agent-Based Models

Nuno Fachada, Vitor V. Lopes, Rui C. Martins, Agostinho C. Rosa

专题命中 记忆与上下文管理 ：agent(title,abstract)

Comments The peer-reviewed version of this paper is published in the International Journal of Parallel Programming at http://dx.doi.org/10.1007/s10766-015-0399-9 . This version is typeset by the authors and differs only in pagination and typographical detail

Journal ref International Journal of Parallel Programming, 45(3), pp. 449-481, 2017

Coordination in State-Dependent Distributed Networks: The Two-Agent Case

Benjamin Larrousse, Samson Lasaulce, Michèle Wigger

专题命中 记忆与上下文管理 ：agent(title,abstract)

Comments Published in 2015 IEEE International Symposium on Information Theory

The Many-agent limit of the Extreme Introvert-Extrovert model

Deepak Dhar, Kevin E. Bassler, R. K. P. Zia

专题命中 记忆与上下文管理 ：agent(title,abstract)

Comments Minor correction in one equation

Comparing Stochastic Differential Equations and Agent-Based Modelling and Simulation for Early-stage Cancer

Grazziela P Figueredo, Peer-Olaf Siebers, Markus R Owen, Jenna Reps, Uwe Aickelin

专题命中 记忆与上下文管理 ：agent(title,abstract)

Comments PLoS ONE, 9 (4), pp. e95150, 2014

Understanding agent-based models of financial markets: a bottom-up approach based on order parameters and phase diagrams

Ribin Lye, James Peng Lung Tan, Siew Ann Cheong

专题命中 记忆与上下文管理 ：agent(title,abstract)

Comments elsarticle.cls, 22 pages, 10 figures

Agent Based Models of Language Competition: Macroscopic descriptions and Order-Disorder transitions

F. Vazquez, X. Castello, M. San Miguel

专题命中 记忆与上下文管理 ：agent(title,abstract)

Comments 30 pages, 11 figures

Equation-Free Multiscale Computations in Social Networks: from Agent-based Modelling to Coarse-grained Stability and Bifurcation Analysis

A. C. Tsoumanis, C. I. Siettos, I. G. Kevrekidis, G. V. Bafas

专题命中 记忆与上下文管理 ：agent(title,abstract)

Journal ref Int J. BIfurcation and Chaos, 20 (11), 3673-3688 (2010)

Heart Rate Monitoring as an Easy Way to Increase Engagement in Human-Agent Interaction

Jérémy Frey

专题命中 记忆与上下文管理 ：agent(title,abstract)

Comments PhyCS - International Conference on Physiological Computing Systems, Feb 2015, Angers, France. SCITEPRESS, \<http://www.phycs.org/\&gt

The Probabilistic Structure of Discrete Agent-Based Models

Sven Banisch

专题命中 记忆与上下文管理 ：agent(title,abstract)

Journal ref Discontinuity, Nonlinearity, and Complexity, 3:281--292, 2014

A three-state kinetic agent-based model to analyze tax evasion dynamics

Nuno Crokidakis

专题命中 记忆与上下文管理 ：agent(title,abstract)

Comments 13 pages, 6 figures, accepted for publication in Physica A

Journal ref Physica A 414, 321 (2014)

Delivery of Liquid Metal to the Target Vessels as Vascular Embolic Agent to Starve Diseased Tissues or Tumors to Death

Qian Wang, Yang Yu, Jing Liu

专题命中 记忆与上下文管理 ：agent(title,abstract)

Comments 21 pages, 10 figures

An agent-based computational model for China's stock market and stock index futures market

Hai-Chuan Xu, Wei Zhang, Xiong Xiong, Wei-Xing Zhou

专题命中 记忆与上下文管理 ：agent(title,abstract)

Journal ref Mathematical Problems in Engineering 2014, 563912 (2014)

Agent-Based Stock Market Model with Endogenous Agents' Impact

Jan A. Lipski, Ryszard Kutner

专题命中 记忆与上下文管理 ：agent(title,abstract)

Comments Submitted to the Journal of Economic Interaction and Coordination

Heterogeneous Enterprises in a Macroeconomic Agent-Based Model

Cornelia Metzig, Mirta Gordon

专题命中 记忆与上下文管理 ：agent(title,abstract)

Agent-based simulations of emotion spreading in online social networks

Milovan Šuvakov, David Garcia, Frank Schweitzer, Bosiljka Tadić

专题命中 记忆与上下文管理 ：agent(title,abstract)

Comments 21 pages, 13 figures

Agent dynamics in kinetic models of wealth exchange

Arnab Chatterjee, Parongama Sen

专题命中 记忆与上下文管理 ：agent(title,abstract)

Comments 6 pages, 6 eps figures, 2 column revtex, to appear in Phys. Rev. E

Journal ref Phys. Rev. E 82 (2010) 056117

Crowd simulation influenced by agent's socio-psychological state

F. Cherif, R. Chighoub

专题命中 记忆与上下文管理 ：agent(title,abstract)

Comments Journal of Computing online at https://sites.google.com/site/journalofcomputing/

Journal ref Journal of Computing, Volume 2, Issue 4, April 2010

Minimal Agent Based Model for Financial Markets I: Origin and Self-Organization of Stylized Facts

V. Alfi, M. Cristelli, L. Pietronero, A. Zaccaria

专题命中 记忆与上下文管理 ：agent(title,abstract)

Minimal Agent Based Model For The Origin And Self-Organization Of Stylized Facts In Financial Markets

V. Alfi, L. Pietronero, A. Zaccaria

专题命中 记忆与上下文管理 ：agent(title,abstract)

Comments 9 pages, 5 figures

Synchronizing to the Environment: Information Theoretic Constraints on Agent Learning

James P. Crutchfield, David P. Feldman

专题命中 记忆与上下文管理 ：agent(title,abstract)

Comments 6 pages, 5 figures, Santa Fe Institute Working Paper 01-03-020, http://www.santafe.edu/projects/CompMech/papers/stte.html

Reliable Post-Retrieval Assembly for Agent Memory: Separating Evidence Extraction from Policy Execution

不要询问LLM追踪新鲜度：一种确定性的内存冲突解决策略

Vikas Reddy, Sumanth Reddy Challaram

机构 * IIT Kgp（印度理工学院科钦分校） 纠错

专题命中 记忆与上下文管理 ：agent(title,comments)；分类 cs.AI、cs.CL

AI总结 针对基于LLM的内存系统中事实冲突解决性能低下的问题，提出用候选提取加Python max(serial)的确定性聚合替代LLM判断，在单跳任务上提升10.8个百分点，并扩展到多跳任务。

Comments 11 pages, 5 tables. Accepted as a poster at the Lifelong Agent Workshop at COLM 2026. Code: https://github.com/cvikasreddy/memory-conflict-resolution

What Gets Lost When Memory Becomes Media? Evaluating AI-Generated Oral History Visualization

当记忆成为媒介时会失去什么？评估人工智能生成的口述历史可视化

Kwangsuk Park, Jaehyun Koo, Jiyeon Lee, Anjung Tan, Hyoungchul Park

专题命中 记忆与上下文管理 ：agent(abstract)；planning(abstract)；multi-agent(abstract)；分类 cs.AI

AI总结 研究散居海外者口述历史可视化中记忆变媒介时的问题，基于口述历史理论设计指标，比较两种管道，发现场景规划与叙事保留冲突，提出基于失败模式的评估框架、冲突分析及系统选择路由协议。

Comments Accepted at ICML 2026 Workshop on Culture x AI: Evaluating AI as a Cultural Technology

Memory as an Attack Surface in LLM Agents: A Study on Multiple-Choice Question Answering

LLM代理中的记忆作为攻击面：多项选择题回答研究

Shahnewaz Karim Sakib, Anindya Bijoy Das

专题命中 记忆与上下文管理 ：agent(abstract)；AI agent(abstract)；tool use(abstract)；分类 cs.AI

AI总结 研究LLM代理中外部记忆组件在多项选择题回答中的脆弱性，通过插入误导记忆进行攻击，实验表明简单记忆操纵即可显著影响答案准确性。

Structured Cognitive Loop for Behavioral Intelligence in Large Language Model Agents (Extended Revision: From Behavioral Architecture to Epistemic Accountability)

大型语言模型代理中行为智能的结构化认知循环（扩展修订：从行为架构到认知问责）

Myung Ho Kim

机构 * JEI University（JEI大学） 纠错

专题命中 记忆与上下文管理 ：agent(abstract)；AI agent(abstract)；planning(abstract)；分类 cs.AI

AI总结 提出结构化认知循环（SCL）架构，通过分离认知、记忆、控制和行动模块，实现LLM代理的可问责行为，在360个任务中成功率86.3%，优于基线方法。

Comments This revised version extends the original SCL framework from a behavioral architecture for reliable LLM agents into a broader architecture of epistemic accountability, integrating context-aware Human-in-the-Loop control, Pool-Gated Retrieval, and the Horizon-Warrant-Commitment structure

MT-OSC: Path for LLMs that Get Lost in Multi-Turn Conversation

MT-OSC：解决大语言模型在多轮对话中迷失的路径

Jyotika Singh, Fang Tu, Miguel Ballesteros, Weiyi Sun, Sandip Ghoshal, Michelle Yuan, Yassine Benajiba, Sujith Ravi, Dan Roth

机构 * Oracle AI 纠错

专题命中 记忆与上下文管理 ：agent(summary_cn,abstract)；分类 cs.CL

AI总结 提出MT-OSC框架，通过后台自动压缩对话历史（Condenser Agent）减少token量，提升多轮对话性能，在13个LLM上验证有效性。

CoMem: Context Management with A Decoupled Long-Context Model

CoMem: 基于解耦长上下文模型的上下文管理

Yuwei Zhang, Chengyu Dong, Shuowei Jin, Changlong Yu, Hejie Cui, Hongye Jin, Xinyang Zhang, Hamed Bonab, Colin Lockard, Jianshu Chen, Zhenyu Shi, Jingbo Shang, Xian Li, Bing Yin

机构 * Halıcıoğlu Data Science Institute, University of California, San Diego（哈里卡卢斯数据科学研究所，加州大学圣地亚哥分校） ； Amazon（亚马逊） 纠错

专题命中 记忆与上下文管理 ：agent(abstract)；workflow(abstract)；agentic(abstract)；分类 cs.LG

AI总结 提出CoMem框架，通过将记忆管理与智能体工作流解耦并采用k步偏移异步流水线，利用奖励驱动训练策略，在SWE-Bench-Verified上实现1.4倍延迟改进且保持大部分性能。

Comments Work in progress

Anticipate and Learn: Unleashing Idle-Time Compute in Proactive Agents

预见与学习：在主动智能体中释放空闲时间计算

Haoyi Hu, Qirong Lyu, Xianghan Kong, Weiwen Liu, Jianghao Lin, Zixuan Guo, Yan Xu, Yasheng Wang, Weinan Zhang, Yong Yu

机构 * Shanghai Jiao Tong University（上海交通大学） ； Tencent（腾讯） 纠错

专题命中 记忆与上下文管理 ：agent(abstract)；AI agent(abstract)；tool use(abstract)；分类 cs.CL

AI总结 提出ProAct主动智能体架构，利用空闲时间计算预测并满足用户未来需求，通过ProActEval基准测试验证其在任务加速、减少用户努力和降低幻觉率方面的显著优势。

Comments 26 pages, 4 figures; code available at https://github.com/AgentACE-AI/ProAct

AutoSOTA: An End-to-End Automated Research System for State-of-the-Art AI Model Discovery

AutoSOTA：面向最先进AI模型发现的端到端自动化研究系统

Yu Li, Chenyang Shao, Xinyang Liu, Ruotong Zhao, Peijie Liu, Hongyuan Su, Zhibin Chen, Qinglong Yang, Anjie Xu, Yi Fang, Qingbin Zeng, Tianxing Li, Jingbo Xu, Fengli Xu, Yong Li, Tie-Yan Liu

机构 * Department of Electronic Engineering, BNRist, Tsinghua University（电子工程系，北京理工大学，清华大学） ； Zhongguancun Academy（中关村学院） ； Peking University（北京大学） ； University of Science and Technology of China（中国科学技术大学） 纠错

专题命中 记忆与上下文管理 ：agent(abstract)；workflow(abstract)；multi-agent(abstract)；分类 cs.CL

AI总结 提出AutoSOTA系统，采用多智能体架构实现从论文复现到模型优化的全自动化，成功发现105个超越原始方法的新SOTA模型。