← Back to all news
arXiv AI By Yifan Zhang, Yunheng Zou, Shaokun Zhang, Jian Hu, Hao Zhang, Binfeng Xu, Jan Kautz, Yi Dong

Agora: Git as Shared Memory for Collective AutoResearch

Read the original on arXiv AI →

Agora is a system that uses Git as a shared memory for autonomous research agents, recording each claim as an immutable commit in an append‑only directed acyclic graph. In a 12‑day run, 13 language‑model workers independently explored a weight‑transfer problem, producing 1,703 contributions that improved a 119.6M‑parameter model’s performance from 3.39 to 1.899 bits per byte. The system’s design includes a diversity‑aware selection rule and an index that tracks the frontier, neglected branches, and verification status of each claim.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
3d ago

MILO: Automated Harness Discovery via Orchestrated Multi-Agent Evolution

arXiv:2609.38349v1 Announce Type: cross Abstract: Modern agentic systems combine an AI model with a harness that controls execution and environmental interactions. Harness design strongly affects lon...

By Prithwish Jana, Mononito Goswami, Hao Liu, Xinyu Li, Langlin Huang, Zhehui Huang, Zhishen Huang, Patrick Bl\"obaum, Anoop Deoras, Purak Jain, Nikos Kanakaris, Sahika Genc
llmsagentsbenchmarks
More like this →
arXiv AI
Sep 7

Iris: Climbing to the Search Frontier

The paper introduces Iris-mini and Iris-pro, two search agents trained at 35B and 397B parameter scales. They use a novel data pipeline that constructs reverse‑engineered multi‑hop queries from web hyperlinks, filters trajectories, and alternates supervised fine‑tuning with reinforcement learning in a process called SFT‑RL climbing. Evaluations on several benchmarks show that, with inference‑time context management, the agents achieve the best open‑source results in their parameter ranges.

By Ziyuan Liu, Hengqi Liu, Zichuan Wang, Yang Qin, Jiachen Liang, Xu Chu, Shaowei Chen, Yuantao Gu, Mu Chuan
agentsreinforcement-learningfine-tuningbenchmarksdata-engineering
More like this →
arXiv AI
Sep 3

Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills

The paper introduces Repo-To-Skill, a method for converting GitHub repositories into reusable AI skills. By distilling operational knowledge from over 1,000 machine‑learning repositories, the authors build the AREX‑Skill Library with more than 5,000 verified skills across 20 areas. Integrating these skills into a research agent—DisCo—yields significant performance boosts on multiple benchmarks, demonstrating the value of reusable, task‑agnostic knowledge.

By Jianlyu Chen, Yuyang Hu, Hongjin Qian, Jiawei Liu, Wenqing Wei, Xiaolong Chen, Defu Lian, Zhicheng Dou, Chaozhuo Li, Qiwei Ye, Zheng Liu
llmsagentsefficiency
More like this →