中文
相关论文

相关论文: SkillGraph: Skill-Augmented Reinforcement Learning…

200 篇论文

Large Language Model (LLM) agents have shown stunning results in complex tasks, yet they often operate in isolation, failing to learn from past experiences. Existing memory-based methods primarily store raw trajectories, which are often…

A persistent skill library allows language model agents to reuse successful strategies across tasks. Maintaining such a library requires three coupled capabilities. The agent selects a relevant skill, utilizes it during execution, and…

人工智能 · 计算机科学 2026-05-13 Yaorui Shi , Yuxin Chen , Zhengxi Lu , Yuchun Miao , Shugui Liu , Qi GU , Xunliang Cai , Xiang Wang , An Zhang

Scaling vision-language models into Visual Multiagent Systems (VMAS) is hindered by two coupled issues. First, communication topologies are fixed before inference, leaving them blind to visual content and query context; second, agent…

人工智能 · 计算机科学 2026-04-21 Zheng Nie , Ruolin Shen , Xinlei Yu , Bo Yin , Jiangning Zhang , Xiaobin Hu

Real-world tool-using agents operate over long-horizon workflows with recurring structure and diverse demands, where effective behavior requires not only invoking atomic tools but also abstracting, and reusing higher-level tool…

Large Language Model (LLM)-based agents have demonstrated remarkable capabilities in complex reasoning and multi-turn interactions but struggle to continuously improve and adapt when deployed in new environments. One promising approach is…

Skill libraries have become a practical way for LLM agents to reuse procedural experience across tasks. However, existing systems typically treat skills as flat, single-resolution prompt blocks. This creates a tension between relevance and…

人工智能 · 计算机科学 2026-05-12 Yongliang Miao , Ziyang Yu , Liang Zhao , Bowen Zhu , Hasibul Haque

Recent advances in Large Language Model Multi-Agent Systems enable scalable orchestration and retrieval of specialized, parallelized subagents, each equipped with hundreds or thousands of Model Context Protocol (MCP) servers and tools.…

计算与语言 · 计算机科学 2025-11-25 Faheem Nizar , Elias Lumer , Anmol Gulati , Pradeep Honaganahalli Basavaraju , Vamse Kumar Subbiah

Large language model (LLM) agents such as OpenClaw rely on reusable skills to perform complex tasks, yet these skills remain largely static after deployment. As a result, similar workflows, tool usage patterns, and failure modes are…

人工智能 · 计算机科学 2026-04-10 Ziyu Ma , Shidong Yang , Yuxiang Ji , Xucong Wang , Yong Wang , Yiming Hu , Tongwen Huang , Xiangxiang Chu

Large language model agents increasingly rely on skill libraries for multi-step tasks, yet these libraries can accumulate persistent defects as skills are added, reused, patched, and linked to changing dependencies. We call this failure…

软件工程 · 计算机科学 2026-05-14 Hongji Pu , Xinyuan Song , Liang Zhao

Agentic large language models often rely on skills, reusable natural language procedures that guide planning, action, and tool use. In practice, skills are typically improved through prompt engineering or by aligning the task LLM itself,…

Skill ecosystems for LLM agents have matured rapidly, yet recent benchmarks show that providing agents with more skills does not monotonically improve performance -- focused sets of 2-3 skills outperform comprehensive documentation, and…

计算与语言 · 计算机科学 2026-04-21 Tianle Xia , Lingxiang Hu , Yiding Sun , Ming Xu , Lan Xu , Siying Wang , Wei Xu , Jie Jiang

Learning from experience is critical for building capable large language model (LLM) agents, yet prevailing self-evolving paradigms remain inefficient: agents learn in isolation, repeatedly rediscover similar behaviors from limited…

计算与语言 · 计算机科学 2026-04-21 Chenxi Wang , Zhuoyun Yu , Xin Xie , Wuguannan Yao , Runnan Fang , Shuofei Qiao , Kexin Cao , Guozhou Zheng , Xiang Qi , Peng Zhang , Shumin Deng

Equipping large language models with explicit skills has emerged as a promising paradigm for enabling autonomous agents to solve complex tasks. Agent skills can be inherently divided into general skills for broad cognitive transfer and…

计算与语言 · 计算机科学 2026-05-28 Jiapeng Zhu , Jianxiang Yu , Yibo Zhao , Chengcheng Han , Qi Gu , Xunliang Cai , Xiang Li , Weining Qian

In recent years, a variety of powerful LLM-based agentic systems have been applied to automate complex tasks through task orchestration. However, existing orchestration methods still face key challenges, including strategy collapse under…

人工智能 · 计算机科学 2026-05-15 Mingda Zhang , Tiesunlong Shen , Haoran Luo , Wenjin Liu , Zikai Xiao , Erik Cambria , Xiaoying Tang

LLM agents must select tools from large API libraries and order them correctly. Existing methods use semantic similarity for both retrieval and ordering, but ordering depends on inter-tool data dependencies that are absent from tool…

人工智能 · 计算机科学 2026-04-23 Hao Liu , Dongyu Li

Current AI agents can flexibly invoke tools and execute complex tasks, yet their long-term advancement is hindered by the lack of systematic accumulation and transfer of skills. Without a unified mechanism for skill consolidation, agents…

Large Language Models (LLMs) increasingly rely on agentic capabilities-iterative retrieval, tool use, and decision-making-to overcome the limits of static, parametric knowledge. Yet existing agentic frameworks treat external information as…

计算与语言 · 计算机科学 2026-04-24 Yuanfu Sun , Kang Li , Dongzhe Fan , Jiajin Liu , Qiaoyu Tan

Advancements in the capabilities of Large Language Models (LLMs) have created a promising foundation for developing autonomous agents. With the right tools, these agents could learn to solve tasks in new environments by accumulating and…

Agent skills provide a lightweight way to adapt LLM agents to specialized domains by storing reusable procedural knowledge in structured files. However, whether downloaded from third parties or self-generated, these skills are often…

人工智能 · 计算机科学 2026-05-28 Hanyu Wang , Yifan Lan , Bochuan Cao , Lu Lin , Jinghui Chen

Dialogue policy plays an important role in task-oriented spoken dialogue systems. It determines how to respond to users. The recently proposed deep reinforcement learning (DRL) approaches have been used for policy optimization. However,…

计算与语言 · 计算机科学 2019-05-28 Lu Chen , Zhi Chen , Bowen Tan , Sishan Long , Milica Gasic , Kai Yu
‹ 上一页 1 2 3 10 下一页 ›