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.
The roadmap of long-horizon agents
| Date | Stars |
|---|---|
| 2026-07-31 | 737 |
| 2026-08-05 | 882 |
| 2026-08-06 | 882 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="center"> <img src="assets/banner.png" alt="Toward Long-Horizon AI Agents — Foundations, Evolution, Harnesses, Optimization, Applications, and Frontiers"/> [](https://openreview.net/pdf?id=HyhfhlbWGh) [](https://www.preprints.org/manuscript/202607.1328) [](https://Long-Horizon-Agents.github.io) [](LICENSE) [](https://github.com/RUC-NLPIR/Awesome-Long-Horizon-Agents) <br> [](https://x.com/kakakbibibi/status/2078076130037514640) [](https://www.xiaohongshu.com/discovery/item/6a5a0270000000001101bf4b?xsec_token=CBBWyPtxwVJZ7VTsxjUlRMpcCzkCH8OxM6_2wfuBLY_8c=&xsec_source=app_share) [](https://mp.weixin.qq.com/s/r9YJYlVAyBZtfMXvAOh5ig) *A curated, continuously-updated reading list accompanying our paper on **long-horizon agents**.* ⭐ ***Star us if you find this useful!*** </div> ## <img src="assets/icons/news.png" height="30" align="top"/> News - **[2026/07]** 📣 The brief introduction of our survey can be found on **[X](https://x.com/kakakbibibi/status/2078076130037514640)** and **[Xiaohongshu](https://www.xiaohongshu.com/discovery/item/6a5a0270000000001101bf4b?xsec_token=CBBWyPtxwVJZ7VTsxjUlRMpcCzkCH8OxM6_2wfuBLY_8c=&xsec_source=app_share)**. - **[2026/07]** 📄 Our paper [**Towards Long-Horizon Agents: A Survey**](https://openreview.net/pdf?id=HyhfhlbWGh) is available on OpenReview. - **[2026/07]** 🚀 We released the paper list for **Towards Long-Horizon Agents: A Survey**, restructured to mirror the paper chapter-by-chapter. - **[2026/07]** 🙌 Contributions are welcome: add a missing work in PR (`[Venue Year] Title. [paper] [code]`). <div align="center"> <img src="assets/horizon.png" width="90%" alt="Time horizon growth of frontier AI agents"/> <br> <em><b>Figure 1.</b> The <b>time horizon</b> of frontier AI agents is growing exponentially, roughly doubling every few months.</em> </div> --- ## <img src="assets/icons/intro.png" height="30" align="top"/> Introduction Large language models have evolved from single-turn chatbots into the decision-making core of autonomous agents. As Figure 1 shows, the time horizon of tasks they can complete unaided is growing exponentially. This surfaces one decisive requirement we call **long horizon**: persistent iteration across reasoning, tool use, observation, and revision over many interdependent steps — from tasks within a single context window to those spanning windows, sessions, or open-ended task streams. Our survey frames **long-horizon agency** as a system-level capability jointly shaped by two forces: - **Externalized harness engineering**: loops and workflows, context and memory, tools and skills, orchestration, hooks, and verification. - **Internalized model optimization**: architecture, data and environment synthesis, pre-/mid-training, fine-tuning, agentic reinforcement learning, on-policy distillation, and self-evolution. The two sides co-evolve through experience and feedback: capabilities first implemented explicitly in the harness may later be internalized into the model policy, while stronger policies in turn enable more capable harnesses. Figure 2 lays out this co-evolutionary landscape end to end. <div align="center"> <img src="assets/landscape.png" width="95%" alt="Landscape of long-horizon agent research"/> <br> <em><b>Figure 2.</b> The la
Excerpt of 132,864 characters
Read on GitHub
138
KABI · Renmin University of China (RUC) · China
62
8
8
Yuyang Hu · China
5
Xiaoxi Li · Renmin University of China · China
3
2
2
1
1
1
Chaoyue He · Nanyang Tech. Univ.
1
1
Shijue Huang · Ph.D. Student in HKUST
1
1
Aidan Lew · Peking University · China
1
zhenyu li · China
1
1
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:3b7f4b86f2a8bcf3, desc:roadmap