中文
相关论文

相关论文: SkillOpt: Executive Strategy for Self-Evolving Age…

200 篇论文

The quality of training data impacts the performance of pre-trained large language models (LMs). Given a fixed budget of tokens, we study how to best select data that leads to good downstream model performance across tasks. We develop a new…

计算与语言 · 计算机科学 2023-08-01 Mayee F. Chen , Nicholas Roberts , Kush Bhatia , Jue Wang , Ce Zhang , Frederic Sala , Christopher Ré

Skills have become the de facto way to enable LLM agents to perform complex real-world tasks with customized instructions, workflows, and tools, but how to learn them automatically and effectively remains unclear. We introduce…

In reinforcement learning applications like robotics, agents usually need to deal with various input/output features when specified with different state/action spaces by their developers or physical restrictions. This indicates unnecessary…

人工智能 · 计算机科学 2022-12-20 Minghuan Liu , Zhengbang Zhu , Menghui Zhu , Yuzheng Zhuang , Weinan Zhang , Jianye Hao

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…

With the rapid evolution of Large Language Model (LLM) agent ecosystems, centralized skill marketplaces have emerged as pivotal infrastructure for augmenting agent capabilities. However, these marketplaces face unprecedented security…

密码学与安全 · 计算机科学 2026-03-24 Zihan Guo , Zhiyu Chen , Xiaohang Nie , Jianghao Lin , Yuanjian Zhou , Weinan Zhang

Most Large Language Model (LLM) agent memory systems rely on a small set of static, hand-designed operations for extracting memory. These fixed procedures hard-code human priors about what to store and how to revise memory, making them…

计算与语言 · 计算机科学 2026-05-26 Haozhen Zhang , Quanyu Long , Jianzhu Bao , Tao Feng , Weizhi Zhang , Haodong Yue , Wenya Wang

Large language model (LLM) agents rely on reusable skills to solve complex tasks. However, existing skill creation approaches treat skills as isolated and static artifacts, limiting their reusability, reliability, and long-term improvement.…

人工智能 · 计算机科学 2026-05-27 Huawei Lin , Peng Li , Jie Song , Fuxin Jiang , Tieying Zhang

Language agents have achieved considerable performance on various complex question-answering tasks by planning with external tools. Despite the incessant exploration in this field, existing language agent systems still struggle with costly,…

计算与语言 · 计算机科学 2024-05-28 Shuofei Qiao , Ningyu Zhang , Runnan Fang , Yujie Luo , Wangchunshu Zhou , Yuchen Eleanor Jiang , Chengfei Lv , Huajun Chen

Vision-language agents have achieved remarkable progress in a variety of multimodal reasoning tasks; however, their learning remains constrained by the limitations of human-annotated supervision. Recent self-rewarding approaches attempt to…

计算机视觉与模式识别 · 计算机科学 2025-11-27 Jiaqi Liu , Kaiwen Xiong , Peng Xia , Yiyang Zhou , Haonian Ji , Lu Feng , Siwei Han , Mingyu Ding , Huaxiu Yao

Automatic Prompt Optimization (APO) has emerged as a critical technique for enhancing Large Language Model (LLM) performance, yet current state-of-the-art methods typically rely on large, labeled gold-standard development sets to compute…

A prerequisite for coding agents to perform tasks on large repositories is code localization - the identification of relevant files, classes, and functions to work on. While repository-level code localization has been performed using…

Large language models (LLMs) excel at solving complex tasks by executing agentic workflows composed of detailed instructions and structured operations. Yet, building general-purpose agents by manually embedding foundation models into…

人工智能 · 计算机科学 2025-08-08 Chia-Tung Ho , Jing Gong , Xufeng Yao , Yunsheng Bai , Abhishek B Akkur , Haoxing Ren

Self-generated skills for web agents are often unstable and can even hurt performance relative to direct acting. We argue that the key bottleneck is not only skill generation quality, but the fact that web skills remain implicit and…

软件工程 · 计算机科学 2026-04-16 Zijian Lu , Yiping Zuo , Yupeng Nie , Xin He , Weibei Fan , Lianyong Qi , Shi Jin

It is desirable for an agent to be able to solve a rich variety of problems that can be specified through language in the same environment. A popular approach towards obtaining such agents is to reuse skills learned in prior tasks to…

机器学习 · 计算机科学 2024-03-19 Geraud Nangue Tasse , Devon Jarvis , Steven James , Benjamin Rosman

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…

LLM agents now draw on growing skill libraries to handle complex tasks. However, injecting more skills does not always improve task completion and can even degrade it. Existing methods still treat skill injection as a static step, selecting…

人工智能 · 计算机科学 2026-05-29 Yanchao Li , Wanhao Liu , Ben Gao , Jiaqing Xie , Zhehong Ai , Na Zou , Yuqiang Li , Tianfan Fu

AI agents can extend their capabilities at inference time by loading reusable skills into context, yet equipping an agent with too many skills, particularly irrelevant ones, degrades performance. As community-driven skill repositories grow,…

人工智能 · 计算机科学 2026-03-31 Fangzhou Li , Pagkratios Tagkopoulos , Ilias Tagkopoulos

Artifact evaluation has been adopted in the Software Engineering (SE) research community for 15 years, substantially improving research reproducibility across major SE conferences. However, this success has introduced a growing scalability…

软件工程 · 计算机科学 2026-02-04 Zhaonan Wu , Yanjie Zhao , Zhenpeng Chen , Zheng Wang , Haoyu Wang

The objective of lifelong reinforcement learning (RL) is to optimize agents which can continuously adapt and interact in changing environments. However, current RL approaches fail drastically when environments are non-stationary and…

机器学习 · 计算机科学 2021-06-17 Kevin Lu , Aditya Grover , Pieter Abbeel , Igor Mordatch

Alignment of Large Language models (LLMs) is crucial for safe and trustworthy deployment in applications. Reinforcement learning from human feedback (RLHF) has emerged as an effective technique to align LLMs to human preferences and broader…