LLM Agent Harnesses

LLM: Large Language Model

Overview

An LLM agent harness surrounds a language model with the mechanisms needed to act: tool interfaces, control loops, context and memory management, persistent state, and execution environments. Common approaches include ReAct-style loops, explicit workflow graphs, typed tool contracts, sandboxes, and verification or recovery steps; newer systems also adapt harnesses using execution traces, search, or reinforcement learning. Researchers evaluate these systems on coding, web, terminal, scientific, and interactive tasks, measuring not only success but also cost, reliability, and safety. A central tension is how much structure helps: added guidance can improve control and recovery, yet may constrain useful behavior, fail to transfer across models or tasks, or make comparisons hard to interpret without specifying the harness.

Latest papers

CardsList

428 papers67 papers in the last four weeks, down 46% on the four weeks before. 0.5% of all new papers.

  1. Tracking Capabilities for Safer Agents

    Mar 1, 2026Martin Odersky, Yaoyu Zhao, Yichen Xu +2AI Agent SafetyTool Access Control for LLM Agents

  2. General Agent Evaluation

    Feb 26, 2026Elron Bandel, Asaf Yehudai, Lilach Eden +12Agent EvaluationComputer-Use Agent Evaluation

  3. VeRO: A Harness for Agents to Optimize Agents

    Feb 25, 2026Varun Ursekar, Apaar Shanker, Veronica Chatrath +2Agent Harness OptimizationLLM Agent Harnesses

  4. Implicit Intelligence -- Evaluating Agents on What Users Don't Say

    Feb 23, 2026Ved Sirdeshmukh, Marc WetterAI Agent EvaluationAI Agent Benchmarks

  5. The LLMbda Calculus: AI Agents, Conversations, and Information Flow

    Feb 23, 2026Zac Garby, Andrew D. Gordon, David SandsPrompt Injection Attacks on AI AgentsLLM Agent Harnesses

  6. EmbeWebAgent: Embedding Web Agents into Custom Enterprise UIs

    Feb 16, 2026Chenyang Ma, Clyde Fare, Matthew Wilson +1Web AgentsTool-Using Agents

  7. AgentFly: Scaling Agentic Reinforcement Learning with Unified Resource System

    Jul 20, 2025Renxi Wang, Bilal El Bouardi, Rifo Ahmad Genadi +6Agentic RLLLM Agent Training