English
Related papers

Related papers: Continual Harness: Online Adaptation for Self-Impr…

200 papers

AI agents are increasingly deployed on complex, domain-specific workflows -- navigating enterprise web applications that require dozens of clicks and form fills, orchestrating multi-step research pipelines that span search, extraction, and…

Artificial Intelligence · Computer Science 2026-05-05 Haebin Seong , Li Yin , Haoran Zhang , Zhan Shi

Harnesses are now central to coding-agent performance, mediating how models interact with tools and execution environments. Yet harness engineering remains a manual craft, because automating it faces a heterogeneous action space across…

Computation and Language · Computer Science 2026-05-19 Jiahang Lin , Shichun Liu , Chengjun Pan , Lizhi Lin , Shihan Dou , Zhiheng Xi , Xuanjing Huang , Hang Yan , Zhenhua Han , Tao Gui , Yu-Gang Jiang

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 embodied tasks remain a fundamental challenge in AI, as current methods rely on hand-engineered rewards or action-labeled demonstrations, neither of which scales. We introduce ASH, an agentic system that learns an embodied…

Artificial Intelligence · Computer Science 2026-05-15 Benjamin Schneider , Xavier Schneider , Victor Zhong , Sun Sun

Embodied agents are expected to operate persistently in dynamic physical environments, continuously acquiring new capabilities over time. Existing approaches to improving agent performance often rely on modifying the agent itself -- through…

Robotics · Computer Science 2026-05-22 Xue Qin , Simin Luan , John See , Cong Yang , Zhijun Li

Despite significant strides in language models in the last few years, when used as agents, such models often try to perform actions that are not just suboptimal for a given state, but are strictly prohibited by the external environment. For…

Computation and Language · Computer Science 2026-03-05 Xinghua Lou , Miguel Lázaro-Gredilla , Antoine Dedieu , Carter Wendelken , Wolfgang Lehrach , Kevin P. Murphy

Large Language Models (LLMs) can generate code from natural language, but their performance is highly sensitive to prompt formulation. We propose a reinforcement-learning-based framework that models prompt refinement as a sequential…

Software Engineering · Computer Science 2026-05-20 Ali Mohammadi Esfahani , Nafiseh Kahani , Samuel A. Ajila

The performance of large language model (LLM) systems depends not only on model weights, but also on their harness: the code that determines what information to store, retrieve, and present to the model. Yet harnesses are still designed…

Artificial Intelligence · Computer Science 2026-03-31 Yoonho Lee , Roshen Nair , Qizheng Zhang , Kangwook Lee , Omar Khattab , Chelsea Finn

Large language models (LLMs)-based code generation for robotic manipulation has recently shown promise by directly translating human instructions into executable code, but existing methods remain noisy, constrained by fixed primitives and…

Robotics · Computer Science 2025-09-26 Yuan Meng , Zhenguo Sun , Max Fest , Xukun Li , Zhenshan Bing , Alois Knoll

Reinforcement learning for language agents increasingly depends on custom harnesses that manage long-running context, multi-turn tool use and multi-agent orchestration. However, porting these harnesses into RL environment interfaces remains…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-26 Binfeng Xu , Hao Zhang , Shaokun Zhang , Songyang Han , Mingjie Liu , Jian Hu , Shizhe Diao , Zhenghui Jin , Yunheng Zou , Michael Demoret , Jan Kautz , Yi Dong

Evaluating instruction-guided image edits requires rewards that reflect subtle human preferences, yet current reward models typically depend on large-scale preference annotation and additional model training. This creates a data-efficiency…

A core quality of general intelligence is the ability to open-endedly expand and evolve its set of mastered skills autonomously. While recent Foundation Model (FM) driven approaches have shown promising results towards this goal, they…

Artificial Intelligence · Computer Science 2026-05-22 Richard Bornemann , Pierluigi Vito Amadori , Antoine Cully

Recent large language models (LLMs) have demonstrated strong capabilities in understanding and generating code, from competitive programming to repository-level software engineering. In emerging agentic systems, code is no longer only a…

General-purpose agents perform tasks in unfamiliar environments without domain-specific manual customization. Yet no study has systematically measured how agent architecture shapes performance across heterogeneous protocols and diverse…

Recent advances in agentic systems increasingly treat code as an executable operational substrate rather than as a disposable output artifact. Prior work such as \emph{Code as Agent Harness} frames validated agent-generated artifacts as…

Software Engineering · Computer Science 2026-05-27 Mariano Garralda-Barrio

LLM agents are shaped not only by their language models, but also by the runtime harness that mediates observation, tool use, action execution, feedback interpretation, and trajectory control. While existing agent adaptation methods mainly…

Artificial Intelligence · Computer Science 2026-05-28 Tianshi Xu , Huifeng Wen , Meng Li

Autonomous robots can benefit greatly from human-provided semantic characterizations of uncertain task environments and states. However, the development of integrated strategies which let robots model, communicate, and act on such 'soft…

Robotics · Computer Science 2023-09-01 Luke Burks , Hunter M. Ray , Jamison McGinley , Sousheel Vunnam , Nisar Ahmed

Multimodal deep search requires an agent to solve open-world problems by chaining search, tool use, and visual reasoning over evolving textual and visual context. Two bottlenecks limit current systems. First, existing tool-use harnesses…

Computation and Language · Computer Science 2026-05-12 Shijue Huang , Hangyu Guo , Chenxin Li , Junting Lu , Xinyu Geng , Zhaochen Su , Zhenyu Li , Shuang Chen , Hongru Wang , Yi R. Fung

This paper studies the next major bottleneck in agentic AI as system scaling, not only model scaling: the design of auditable, persistent, modular, and verifiable architectures around foundation models. We refer to this shift as scaling the…

Artificial Intelligence · Computer Science 2026-05-26 Shangding Gu

Graphical User Interface (GUI) task automation constitutes a critical frontier in artificial intelligence research. While effective GUI agents synergistically integrate planning and grounding capabilities, current methodologies exhibit two…

Artificial Intelligence · Computer Science 2025-11-17 Yuan Zhao , Hualei Zhu , Tingyu Jiang , Shen Li , Xiaohang Xu , Hao Henry Wang
‹ Prev 1 2 3 10 Next ›