Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Agent Harness for Large Language Model Agents: A Survey. Survey on LLM agentharnessengineering with a taxonomy. 110+papers, 23 systems analyzed.
| Date | Stars |
|---|---|
| 2026-07-31 | 320 |
| 2026-08-05 | 321 |
| 2026-08-06 | 321 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="center"> [English](README.md) | [中文](README_zh.md) # Agent Harness for Large Language Model Agents: A Survey [](https://github.com/Gloriaameng/LLM-Agent-Harness-Survey/stargazers) [](LICENSE) []() []() [](https://huggingface.co/datasets/GloriaaaM/LLM-Agent-Harness-Survey) [](https://doi.org/10.20944/preprints202604.0428.v3) </div> <p align="center"> <img src="assets/architecture_diagram.png" width="720" alt="H=(E,T,C,S,L,V) Six-Component Architecture"/> </p> > ⭐ **This repo is actively maintained. If you find it useful, please star the repo to stay updated and help others find it.** --- > **The agent execution harness — not the model — is the primary determinant of agent reliability at scale.** > This survey formalizes the harness as a first-class architectural object **H = (E, T, C, S, L, V)**, surveys 110+ papers, blogs and reports across 23 systems, and maps 9 open technical challenges. > 📄 **[Read the Paper](./Agent_Harness_for_LLM_Agents__A_Survey_v3.pdf)** > 🌐 **[Preprints Version (v3)](https://www.preprints.org/manuscript/202604.0428/v3)** > ✉️ Corrections & suggestions: [email protected] (Qianyu Meng); [email protected] (Yanan Wang); [email protected] (Liyi Chen) If you find this survey useful, please cite: ```bibtex @article{meng2026agentharness, title = {Agent Harness for Large Language Model Agents: A Survey}, author = {Meng, Qianyu and Wang, Yanan and Chen, Liyi and Wu, Wei and Li, Yihang and Jiang, Wenyuan and Wang, Qimeng and Lu, Chengqiang and Gao, Yan and Wu, Yi and Hu, Yao}, year = {2026}, doi = {10.20944/preprints202604.0428.v3}, url = {https://www.preprints.org/manuscript/202604.0428/v3}, publisher = {Preprints}, } ``` --- ## 🆕 News & Updates - **[2026-04-03]** Initial release - **[2026-04-07]** Repo updated - **[2026-04-09]** Preprint released - **[2026-04-14]** Citation Updated --- ## Table of Contents - [Overview](#overview) - [Historical Timeline](#historical-timeline) - [Harness Completeness Matrix](#harness-completeness-matrix) - [Paper List](#paper-list) - [Historical Lineages](#historical-lineages) - [Harness Taxonomy](#harness-taxonomy) - [Technical Challenges](#technical-challenges) - [Security & Sandboxing](#security--sandboxing) - [Evaluation & Benchmarking](#evaluation--benchmarking) - [Protocol Standardization](#protocol-standardization) - [Runtime Context Management](#runtime-context-management) - [Tool Use & Registry](#tool-use--registry) - [Memory Architecture](#memory-architecture) - [Planning & Reasoning](#planning--reasoning) - [Multi-Agent Coordination](#multi-agent-coordination) - [Compute Economics](#compute-economics) - [Emerging Topics](#emerging-topics) - [Future Directions](#future-directions) - [Citation](#citation) - [Update Log](#update-log) --- ## Overview LLM agents are increasingly deployed in agentic settings where they autonomously plan, use tools, and act in multi-step environments. The dominant narrative attributes agent performance to the underlying model. **This survey challenges that assumption.** We introduce a formal definition of the **agent execution harness** as a six-component tuple: | Component | Symbol | Role | |-----------|--------|------| | Execution Loop | **E** | Observe-think-act cycle, termination conditions, error recovery | | Tool Registry | **T** | Typed tool catalog, routing, monitoring, schema validation | | Context Manager
Excerpt of 49,162 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:8c713a090d3842e5, topic:llm
matched fp:8c713a090d3842e5, topic:agent-framework
matched fp:8c713a090d3842e5, topic:awesome-list