English
Related papers

Related papers: SkillEvolver: Skill Learning as a Meta-Skill

200 papers

Large language models (LLMs) still struggle with the rigorous reasoning demands of hard competitive programming. While recent multi-agent frameworks attempt to bridge this reliability gap, they remain fundamentally stateless: they rely on…

Artificial Intelligence · Computer Science 2026-05-18 Han Li , Jinyu Tian , Rili Feng , Yuqiao Du , Chong Zheng , Chenyu Wang , Chenchen Liu , Shihao Li , Xinping Lei , Yifan Yao , Weihao Xie , Letian Zhu , Jiaheng Liu

LLM agents benefit from reusable skills, yet test-time tasks often require guidance more specific than a static skill library can provide. We propose \emph{SkillTTA}, a Test-Time Adaptive Skill Synthesis method that retrieves a small set of…

Computation and Language · Computer Science 2026-05-19 Jingxing Wang , Chenyu Zhou , Zhihui Fu , Jun Wang , Weiwen Liu , Weinan Zhang , Jianghao Lin

Reinforcement learning (RL) has emerged as a powerful paradigm for achieving online agile navigation with quadrotors. Despite this success, policies trained via standard RL typically fail to generalize across significant dynamic variations,…

Robotics · Computer Science 2026-03-12 Jin Zhou , Dongcheng Cao , Xian Wang , Shuo Li

Offline reinforcement learning, by learning from a fixed dataset, makes it possible to learn agent behaviors without interacting with the environment. However, depending on the quality of the offline dataset, such pre-trained agents may…

Machine Learning · Computer Science 2022-10-26 Yi Zhao , Rinu Boney , Alexander Ilin , Juho Kannala , Joni Pajarinen

As large language models (LLMs) transition into autonomous agents integrated with extensive tool ecosystems, traditional routing heuristics increasingly succumb to context pollution and "overthinking". We argue that the bottleneck is not a…

Artificial Intelligence · Computer Science 2026-04-21 Eren Unlu

Current LLM coding agents are predominantly trained on composite benchmarks (e.g., bug fixing), which often leads to task-specific overfitting and limited generalization. To address this, we propose a novel scaling paradigm that shifts the…

Software Engineering · Computer Science 2026-04-28 Yingwei Ma , Yue Liu , Xinlong Yang , Yanhao Li , Kelin Fu , Yibo Miao , Yuchong Xie , Zhexu Wang , Shing-Chi Cheung

Graphical User Interface (GUI) agents can automate complex tasks across digital environments, but their development is hindered by the scarcity of high-quality trajectory data for training. Existing approaches rely on expensive human…

Computation and Language · Computer Science 2025-03-04 Yiheng Xu , Dunjie Lu , Zhennan Shen , Junli Wang , Zekun Wang , Yuchen Mao , Caiming Xiong , Tao Yu

To integrate seamlessly into real-world software engineering, Code Agents must evolve from passive instruction followers into proactive collaborative partners. However, current evaluation paradigms predominantly reward "guessing" user…

Software Engineering · Computer Science 2026-03-03 Jialin Li , Yuan Wu , Yi Chang

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…

Software Engineering · Computer Science 2026-05-14 Hongji Pu , Xinyuan Song , Liang Zhao

Reinforcement learning (RL) agents improve through trial-and-error, but when reward is sparse and the agent cannot discover successful action sequences, learning stagnates. This has been a notable problem in training deep RL agents to…

Artificial Intelligence · Computer Science 2018-02-27 Evan Zheran Liu , Kelvin Guu , Panupong Pasupat , Tianlin Shi , Percy Liang

Large language models are increasingly expected to serve as general-purpose agents that interact with external, stateful tool environments. The Model Context Protocol (MCP) and broader agent skills offer a unified interface for connecting…

Automatic multi-agent systems aim to instantiate agent workflows without relying on manually designed or fixed orchestration. However, existing automatic MAS approaches remain only partially adaptive: they either perform training-free…

Artificial Intelligence · Computer Science 2026-05-15 Yaolun Zhang , Yujie Zhao , Nan Wang , Yiran Wu , Jiayu Chang , Yizhao Chen , Qingyun Wu , Jishen Zhao , Huazheng Wang

Mobile GUI agents powered by large foundation models enable autonomous task execution, but frequent updates altering UI appearance and reorganizing workflows cause agents trained on historical data to fail. Despite surface changes,…

Artificial Intelligence · Computer Science 2026-02-03 Libo Sun , Jiwen Zhang , Siyuan Wang , Zhongyu Wei

Heavy supervised fine-tuning on a target domain can strongly suppress capabilities that were present in the base model. We study this phenomenon in formal mathematics using Goedel-Prover-V2, an open-source model heavily trained on 1.8…

Artificial Intelligence · Computer Science 2026-04-10 Jui-Hui Chung , Hongzhou Lin , Lai Jiang , Shange Tang , Chi Jin

Multi-agent AI systems have proven effective for complex reasoning. These systems are compounded by specialized agents, which collaborate through explicit communication, but incur substantial computational overhead. A natural question…

Artificial Intelligence · Computer Science 2026-01-15 Xiaoxiao Li

Recent advances in multimodal web agents often rely on increased inference-time computation, including rollout search, verifier passes, offline skill discovery, and specialist model stacks. This raises a central question: can a web agent…

Artificial Intelligence · Computer Science 2026-05-27 Yubo Li , Yidi Miao , Yuntian Shen , Yuxin Liu

Scaffolding Large Language Models (LLMs) into multi-agent systems often improves performance on complex tasks, but the safety impact of such scaffolds has not been thoroughly explored. We introduce AgentBreeder, a framework for…

Cryptography and Security · Computer Science 2025-10-15 J Rosser , Jakob Foerster

Training large language models to acquire specific skills remains a challenging endeavor. Conventional training approaches often struggle with data distribution imbalances and inadequacies in objective functions that do not align well with…

Computation and Language · Computer Science 2025-02-18 So Kuroki , Taishi Nakamura , Takuya Akiba , Yujin Tang

Large language model (LLM) agents are increasingly equipped with memory, which are stored experience and reusable guidance that can improve task-solving performance. Recent \emph{self-evolving} systems update memory based on interaction…

Artificial Intelligence · Computer Science 2026-02-03 Yaolun Zhang , Yiran Wu , Yijiong Yu , Qingyun Wu , Huazheng 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…

Machine Learning · Computer Science 2021-06-17 Kevin Lu , Aditya Grover , Pieter Abbeel , Igor Mordatch