Related papers: Natural-Language Agent Harnesses
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…
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…
Recent advances on large language models (LLMs) enable researchers and developers to build autonomous language agents that can automatically solve various tasks and interact with environments, humans, and other agents using natural language…
Language-model agent systems commonly rely on reactive prompting, in which a single instruction guides the model through an open-ended sequence of reasoning and tool-use steps, leaving control flow and intermediate state implicit and making…
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…
AI agents -- systems that combine foundation models with reasoning, planning, memory, and tool use -- are rapidly becoming a practical interface between natural-language intent and real-world computation. This survey synthesizes the…
When humans conceive how to perform a particular task, they do so hierarchically: splitting higher-level tasks into smaller sub-tasks. However, in the literature on natural language (NL) command of situated agents, most works have treated…
Intelligent agents such as robots are increasingly deployed in real-world, safety-critical settings. It is vital that these agents are able to explain the reasoning behind their decisions to human counterparts, however, their behavior is…
Natural language serves as the primary mode of communication when an intelligent agent with a physical presence engages with human beings. While a plethora of research focuses on natural language understanding (NLU), encompassing endeavors…
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…
Industry practitioners and academic researchers regularly use multi-agent systems to accelerate their work, but the applications through which users operate these systems do not provide a simple, unified mechanism for scalably managing…
Harness engineering has emerged as an important inference-time technique for large language model (LLM) agents, aiming to improve long-term performance through task decomposition and guided execution. However, more elaborate harnesses are…
AI agents that interact with the real world through tool calls pose fundamental safety challenges: agents might leak private information, cause unintended side effects, or be manipulated through prompt injection. To address these…
AI agents are entering high-risk production settings, where they use tools, retain context, follow policies, handle private data, and interact with users over multiple turns. Yet many evaluation methods still judge isolated outputs or…
The dominant paradigm for building LLM based agents is the Agent Loop, an iterative cycle where a single language model decides what to do next by reading an ever growing context window. This paradigm has three structural weaknesses:…
Fast expansion of natural language functionality of intelligent virtual agents is critical for achieving engaging and informative interactions. However, developing accurate models for new natural language domains is a time and data…
Intelligent agents such as robots are increasingly deployed in real-world, safety-critical settings. It is vital that these agents are able to explain the reasoning behind their decisions to human counterparts; however, their behavior is…
AI agents have been developed for complex real-world tasks from coding to customer service. But AI agent evaluations suffer from many challenges that undermine our understanding of how well agents really work. We introduce the Holistic…
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…
Recent advancements on Large Language Models (LLMs) enable AI Agents to automatically generate and execute multi-step plans to solve complex tasks. However, since LLM's content generation process is hardly controllable, current LLM-based…