← Back to all news
arXiv AI By Ziyang Zeng, Tingyang Chen, Jia Deng, Qiyao Wang, Shuo Tang, Yike Yang, Tao Ren, Wayne Xin Zhao, Feng Chang, Jujie He, Chuan Hao, Ran Tao, Bryan Dai

WorkFactory: Turning Professional Intents into Executable Work for Scalable Agent Training

Read the original on arXiv AI →

WorkFactory is a scalable framework that transforms professional intents into executable tasks by building an information support graph and using probe executions to detect and repair support failures. The authors generated 112,686 tasks across 612 occupations and fine‑tuned Qwen models (4B, 27B, 35B-A3B) to create the WorkPilot family, which outperforms base models on four professional‑work benchmarks. The study shows that planning and repair reduce task environment defects and improve downstream performance, with diminishing returns observed as model size increases.

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
Sep 30

SkillGym: Training Skill-Use Agents with Automatic Verifiable Environment Generation

SkillGym is an automatic pipeline that generates verifiable environments for training skill-use agents. It crawls internet skills, filters for reproducible workflows, and uses a builder‑reviewer process to create difficulty‑controlled tasks with reference solutions and verifiers. The system builds 6.8k environments, collects 19k successful trajectories, and fine‑tunes LLMs from 2B to 122B parameters, improving performance and skill invocation rates.

By Renxi Wang, Mingshan Hee, Fajri Koto, Timothy Baldwin, Haonan Li
llmsagentsfine-tuningbenchmarks
More like this →
arXiv AI
Oct 15

SkillHorizon: Constructing Long-Horizon Agent Tasks through Skill Composition

arXiv:2610.14966v1 Announce Type: new Abstract: Long-horizon agents must complete workflows in which later activities depend on earlier outputs and changes to shared state. A key challenge for evalua...

By Yuxuan Liu, Zhaochen Su, Hangyu Guo, Shijue Huang, Zhixiong Zhang, Kawai Chung, Zhongwei Xie, Tianshi Zheng, Wei Fan, Qing Zong, Haochen Shi, Baixuan Xu, Haoran Li, Yangqiu Song
llmsagentsbenchmarks
More like this →
arXiv Computation and Language
Oct 15

Interlock: From Local Correctness to Task Completion in Long-Horizon Agents

Interlock is a framework that transforms long‑horizon tasks into typed completion graphs, linking evidence, decisions, and required effects through grounding, coupling, and realization edges. It compiles these graphs into a resettable workspace, a public request, and an evaluation rubric, and uses source‑coverage, public‑input, and agent‑as‑judge reviews to ensure that all mandatory requirements are met. Fine‑tuning Qwen3.6 backbones on Interlock‑generated trajectories improves pass rates on AutomationBench, JobBench, and Harvey LAB, showing that the synthesized experience benefits external task environments.

By Linji Hao, Yanji He, Zihan Wang, Hansi Yang, Jiayuan Zhang, Hongyan Hao, Qi Gu, Yan Feng, Han Wu
llmsagentsfine-tuning
More like this →