LLM Agent Harnesses

LLM: Large Language Model

Ask about this topic

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

389 papers118 papers in the last four weeks, up 103% on the four weeks before. 0.7% of all new papers.

  1. ANX: Protocol-First Design for AI Agent Interaction with a Supporting 3EX Decoupled Architecture

    Apr 6, 2026Xu MingzeLLM AgentsLLM Agent Harnesses

    Hangzhou Ziyou Data Technology Co., Ltd., Hangzhou 310000, China

  2. Inside the Scaffold: A Source-Code Taxonomy of Coding Agent Architectures

    Apr 3, 2026Benjamin RombautCoding AgentsLLM Agent Orchestration

  3. SkVM: Revisiting Language VM for Skills across Heterogenous LLMs and Harnesses

    Apr 3, 2026Le Chen, Erhu Feng, Yubin Xia +1LLM AgentsLLM Agent Harnesses

    Shanghai Jiao Tong University Shanghai, China

  4. In harmony with gpt-oss

    Apr 1, 2026Borislav MavrinAI Agent BenchmarksTool-Use Evaluation

  5. Synergy: A Next-Generation General-Purpose Agent for Open Agentic Web

    Mar 30, 2026Xiaohang Nie, Zihan Guo, Kezhuo Yang +9Web AgentsLLM Agent Harnesses

    Shanghai Innovation Institute · Harbin Institute of Technology · Holos Engineering +3

  6. Meta-Harness: End-to-End Optimization of Model Harnesses

    Mar 30, 2026Yoonho Lee, Roshen Nair, Qizheng Zhang +3LLM Agent HarnessesLarge Language Model-Guided Optimization

    Stanford · KRAFTON · MIT

  7. Natural-Language Agent Harnesses

    Mar 26, 2026Linyue Pan, Lexiao Zou, Shuo Guo +2LLM Agent HarnessesLLM Agent Orchestration

    Shenzhen International Graduate School, Tsinghua University · Harbin Institute of Technology (Shenzhen)

  8. FluxEDA: A Unified Execution Infrastructure for Stateful Agentic EDA

    Mar 26, 2026Zhengrui Chen, Zixuan Song, Yu Li +2Electronic Design AutomationLLM Agent Harnesses

    Zhejiang University, Hangzhou, China

  9. Reasoner-Executor-Synthesizer: Scalable Agentic Architecture with Static O(1) Context Window

    Mar 23, 2026Ivan DobrovolskyiAgentic RAGLLM Hallucination Mitigation

    Walmart Global Tech, Sunnyvale, CA, USA

  10. Herding CATs: ALARA for Agent Harness Engineering in Portable Composable Multi-Agent Teams

    Mar 20, 2026Christopher J. Agostino, Nayan D'SouzaLLM Agent HarnessesMulti-Agent Systems

    NPC Worldwide, Bloomington, IN, USA · Celeria, Inc., Bloomington, IN, USA · Department of Linguistics, Indiana University, Bloomington, IN, USA

  11. AI Agents Can Already Autonomously Perform Experimental High Energy Physics

    Mar 20, 2026Eric A. Moreno, Samuel Bright-Thonney, Andrzej Novak +2Autonomous Research AgentsAI Agents for Scientific Discovery

    Department of Physics, Massachusetts Institute of Technology · NSF AI Institute for Artificial Intelligence and Fundamental Interactions · CERN

  12. Agentic Harness for Real-World Compilers

    Mar 20, 2026Yingwei Zheng, Cong Li, Shaohua Li +2LLM Agent HarnessesAutomated Program Repair

    Southern University of Science and Technology · ETH Zurich · The Chinese University of Hong Kong

  13. Exploring the Agentic Frontier of Verilog Code Generation

    Mar 19, 2026Patrick Yubeaton, Siddharth Garg, Chinmay HegdeCode GenerationAgentic Code Generation

    New York University, Tandon School of Engineering, Brooklyn, NY

  14. ProRL Agent: Rollout-as-a-Service for RL Training of Multi-Turn LLM Agents

    Mar 19, 2026Hao Zhang, Mingjie Liu, Shaokun Zhang +10LLM Agent TrainingLLM Agent Harnesses

  15. Interpretable Context Methodology: Folder Structure as Agentic Architecture

    Mar 17, 2026Jake Van Clief, David McDermottLLM Agent OrchestrationLLM Agents

    Eduba, University of Edinburgh, Palm Coast, Florida, USA

  16. Protein Design with Agent Rosetta: A Case Study for Specialized Scientific Agents

    Mar 16, 2026Jacopo Teneggi, S. M. Bargeen A. Turzo, Tanya Marwah +4Tool-Augmented Language Model AgentsAI Agents for Scientific Discovery

    Polymathic AI · Johns Hopkins University · Center for Computational Biology, Flatiron Institute +3

  17. The Agentic Researcher: A Practical Guide to AI-Assisted Research in Mathematics and Machine Learning

    Mar 16, 2026Max Zimmer, Nico Pelleriti, Christophe Roux +1AI-Assisted Scientific ResearchAutonomous Research Agents

    Department for AI in Society, Science, and Technology, Zuse Institute Berlin, Germany · Institute of Mathematics, Technische Universität Berlin, Germany

  18. Agent Lifecycle Toolkit (ALTK): Reusable Middleware Components for Robust AI Agents

    Mar 16, 2026Zidane Wright, Jason Tsay, Anupama Murthi +8AI Agent ReliabilityRuntime Enforcement for AI Agents

    IBM Research, New York, NY, USA · IBM Research, Haifa, Israel · IBM, Argentina

  19. Quine: Realizing LLM Agents as Native POSIX Processes

    Mar 8, 2026Hao KeLLM Agent OrchestrationLLM Agents

    Independent Researcher, Bloomington, IN, USA

  20. Turn: A Language for Agentic Computation

    Mar 7, 2026Muyukani KizitoLLM AgentsLLM Agent Harnesses

    Turn Lang · Prescott Data

  21. Agentics 2.0: Logical Transduction Algebra for Agentic Data Workflows

    Mar 4, 2026Alfio Massimiliano Gliozzo, Junkyu Lee, Nahuel DefosseAgentic WorkflowsLLM Agent Harnesses

    IBM

  22. REGAL: A Registry-Driven Architecture for Deterministic Grounding of Agentic AI in Enterprise Telemetry

    Mar 3, 2026Yuvraj AgrawalLLM GroundingLLM Agents

    Adobe Inc.

  23. Tracking Capabilities for Safer Agents

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

    EPFL Lausanne, Switzerland

  24. General Agent Evaluation

    Feb 26, 2026Elron Bandel, Asaf Yehudai, Lilach Eden +12Agent EvaluationAutomated Agent Evaluation

    IBM Research · MIT

  25. VeRO: A Harness for Agents to Optimize Agents

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

    Scale AI.

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

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

    Applied Machine Learning Research

  27. 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

    University of Nottingham, Nottingham, UK · University of Edinburgh, Edinburgh, UK · Chalmers University of Technology and University of Gothenburg, Gothenburg, Sweden

  28. EmbeWebAgent: Embedding Web Agents into Any Customized UI

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

    IBM Research Europe, UK · University of Oxford

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

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

    Mohamed bin Zayed University of Artificial Intelligence · University of California, Los Angeles