English
Related papers

Related papers: Remember Your Trace: Memory-Guided Long-Horizon Ag…

200 papers

Recent advancements in multi-agent systems have demonstrated significant potential for enhancing creative task performance, such as long video generation. This study introduces three innovations to improve multi-agent collaboration. First,…

Multiagent Systems · Computer Science 2025-10-28 Zheng Wei , Mingchen Li , Zeqian Zhang , Ruibin Yuan , Pan Hui , Huamin Qu , James Evans , Maneesh Agrawala , Anyi Rao

Memory-augmented Large Language Models (LLMs) are essential for developing capable, long-term AI agents. Recently, applying Reinforcement Learning (RL) to optimize memory operations, such as extraction, updating, and retrieval, has emerged…

Computation and Language · Computer Science 2026-04-08 Ziliang Guo , Ziheng Li , Bo Tang , Feiyu Xiong , Zhiyu Li

Memory is essential for enabling large language models to support long-horizon reasoning, yet existing memory systems remain unreliable and difficult to debug. Tracing memory's dynamic evolution is crucial to understand how information is…

Long-term memory is one of the key factors influencing the reasoning capabilities of Large Language Model Agents (LLM Agents). Incorporating a memory mechanism that effectively integrates past interactions can significantly enhance…

Computation and Language · Computer Science 2025-08-01 Haoran Sun , Shaoning Zeng

We introduce \emph{Memento-Skills}, a generalist, continually-learnable LLM agent system that functions as an \emph{agent-designing agent}: it autonomously constructs, adapts, and improves task-specific agents through experience. The system…

Long-horizon code generation requires sustained context and adaptive expertise across domains. Current multi-agent systems use static workflows that cannot adapt when runtime analysis reveals unanticipated complexity. We propose AgentSpawn,…

Software Engineering · Computer Science 2026-02-10 Igor Costa

Agentic frameworks powered by Large Language Models (LLMs) can be useful tools in scientific workflows by enabling human-AI co-creation. A key challenge is recommending the next steps during workflow creation without relying solely on LLMs,…

Recent progress in Large Language Models (LLMs) has drawn attention to their potential for accelerating drug discovery. However, a central problem remains: translating theoretical ideas into robust implementations in the highly specialized…

Machine Learning · Computer Science 2025-03-06 Sizhe Liu , Yizhou Lu , Siyu Chen , Xiyang Hu , Jieyu Zhao , Yingzhou Lu , Yue Zhao

Mental health assessment is crucial for early intervention and effective treatment, yet traditional clinician-based approaches are limited by the shortage of qualified professionals. Recent advances in artificial intelligence have sparked…

Computation and Language · Computer Science 2025-08-18 Jinpeng Hu , Ao Wang , Qianqian Xie , Hui Ma , Zhuo Li , Dan Guo

Agent-assisted memory recall is one critical research problem in the field of human-computer interaction. In conventional methods, the agent can retrieve information from its equipped memory module to help the person recall incomplete or…

Artificial Intelligence · Computer Science 2025-08-01 Qian Zhao , Zhuo Sun , Bin Guo , Zhiwen Yu

Software documentation frequently drifts from executable logic as codebases evolve, creating technical debt that degrades maintainability and causes downstream API misuse. While static analysis tools can detect the absence of documentation,…

Software Engineering · Computer Science 2026-05-05 Sidhesh Badrinarayan , Adithya Parthasarathy

Language-model-based agents operating over extended interaction horizons face persistent challenges in preserving temporally grounded information and maintaining behavioral consistency across sessions, a failure mode we term soul erosion.…

Computation and Language · Computer Science 2026-01-29 Yang Li , Jiaxiang Liu , Yusong Wang , Yujie Wu , Mingkun Xu

LLM agents increasingly rely on memory mechanisms to reuse knowledge from past problem-solving experiences. However, existing methods typically construct memory for a single agent and reuse it with the same underlying model, tightly…

Artificial Intelligence · Computer Science 2026-05-29 Yurui Chang , Yiran Wu , Qingyun Wu , Lu Lin

The rapid development of large vision-language model (VLM) has greatly promoted the research of GUI agent. However, GUI agents still face significant challenges in handling long-horizon tasks. First, single-agent models struggle to balance…

Artificial Intelligence · Computer Science 2026-03-05 Zehao Deng , Tianjie Ju , Zheng Wu , Zhuosheng Zhang , Gongshen Liu

Long-term memory is crucial for agents in specialized web environments, where success depends on recalling interface affordances, state dynamics, workflows, and recurring failure modes. However, existing memory benchmarks for agents mostly…

Computation and Language · Computer Science 2026-05-13 Di Wu , Zixiang Ji , Asmi Kawatkar , Bryan Kwan , Jia-Chen Gu , Nanyun Peng , Kai-Wei Chang

In this work, we propose MetaAgent, an agentic paradigm inspired by the principle of learning-by-doing, where expertise is developed through hands-on practice and continual self-improvement. MetaAgent starts with a minimal workflow,…

Artificial Intelligence · Computer Science 2025-09-03 Hongjin Qian , Zheng Liu

LLM-based web agents show immense promise for information seeking, yet their effectiveness on long-horizon tasks is hindered by a fundamental trade-off in context management. Prevailing ReAct-based agents suffer from context saturation as…

Large Language Model (LLM) web agents often struggle with long-horizon web navigation and web task completion in new websites, producing inefficient action sequences unless fine-tuned on environment-specific data. We show that…

The inherent non-deterministic nature of autonomous agents, particularly within low-code/no-code (LCNC) environments, presents significant reliability challenges. Agents can become trapped in unforeseen loops, generate inaccurate outputs,…

Artificial Intelligence · Computer Science 2025-09-25 Jiexi Xu

Code localization is a fundamental challenge in repository-level software engineering tasks such as bug fixing. While existing methods equip language agents with comprehensive tools/interfaces to fetch information from the repository, they…

Software Engineering · Computer Science 2026-02-10 Boshi Wang , Weijian Xu , Yunsheng Li , Mei Gao , Yujia Xie , Huan Sun , Dongdong Chen