The paper introduces a work-centric framework for understanding and optimizing work agents, which combine foundation models with runtime harnesses to perform tasks in stateful workspaces. It defines two key dimensions—work persistence and work openness—to characterize working conditions and classifies digital work into five forms based on task scope and organization. The authors identify five core capability families necessary for reliable execution, explore optimization strategies for models and harnesses, and evaluate existing metrics from the perspective of verifiable work outcomes.
By Zishan Xu, Enjun Du, Mingqi Gao, Cheng Yang, Junhao Shen, Zirong Chen, Zhiyuan Yao, Yifu Guo, Yuquan Lu, Jinyang Huang, Zhengxi Lu, Siyi Liu, Ziyu Zheng, Yongqi Zhang, Difan Zou, Weiwen Liu
The paper introduces WorkForge, a scalable synthesis framework that builds verifiable work‑agent environments from real‑world resources. By extracting factual anchors from expert workflows and associated files, WorkForge generates task instructions, solution plans, and verifiers that remain traceable to observable workspace evidence. The authors constructed 16.7K environments across 40 professional domains, demonstrating significant performance gains for large language models such as Qwen3.5-35B-A3B-Base and Qwen3.5-27B.
By Jiazheng Zhang, Long Ma, Yunxian Yang, Zhiheng Xi, Zhikai Lei, Yajie Yang, Chenyang Liao, Enyu Zhou, Yang Nan, Yuchen Tian, Senjie Jin, Yibo Wang, Wei He, Boyang Liu, Jixuan Huang, Xin Guo, Zhezheng Hao, Xinbing Liang, Zhihao Zhang, Changzhi Zhou, Wiggin Zhou, Tao Gui, Qi Zhang, Xuanjing Huang, Clarenceai, Aiden Adams
Harness-Bench is a diagnostic benchmark that evaluates how different harness configurations affect LLM agent performance in realistic workflows. It tests 106 sandboxed offline tasks across multiple model backends, recording artifacts, execution traces, and usage statistics to analyze completion, process quality, efficiency, and failure behavior. The study finds significant variation in outcomes across model-harness pairings, indicating that agent capability should be reported at the configuration level rather than solely by the base model.
By Yilun Yao, Xinyu Tan, Chao-Hsuan Liu, Yaoming Li, Zhengyang Wang, Zongwei Lv, Wenhan Yu, Zhewen Tan, Yuxuan Tian, Lin Sun, Xiangzheng Zhang, Guangxiang Zhao, Tong Yang
arXiv:2608. 05013v1 Announce Type: cross Abstract: LLM agents are increasingly applied to open-ended everyday requests that span work, study, and life.
By Jingsheng Zheng, Xinyuan Fang, Jintian Zhang, Zhengke Gui, Huajun Chen, Ningyu Zhang
The paper proposes a new way to describe benchmarks for AI systems that perform knowledge work, outlining four explicit fields: represented activity, tested setting, required work product, and evaluated result. It builds an inventory of 18 work activities from O*NET to enable activity-level reporting across occupations, and evaluates these activities for semantic coherence, algorithm sensitivity, ontology legibility, and human interpretability. The authors apply their framework to three existing benchmarks—GDPval, OfficeQA Pro, and APEX-SWE—to show how different aspects of work can be captured within the same representation.
By Yining Hua, Hongbin Na, Cyrus Ayubcha, Levi Lian
AgentEvolver is a system that enables agents to develop reusable capabilities while executing tasks, without altering the underlying foundation model. It uses eight entity families to expose operations, methods, agents, control flow, interfaces, and state for revision, coordinated by a shared Runtime and persistent planning. In evaluations on SWE-bench Pro Public, it achieved an 82.08% resolution rate, demonstrating retained capabilities across subsequent website, game, and research tasks, though some objectives remained incomplete.
By Wentao Zhang, Fuchao Yang, Yilei Zhao, Xinrun Wang, Bo An
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
The paper investigates how large language model agents handle long‑horizon tasks and finds that verification is crucial for success but often occurs too late. It shows that sharing a common context dilutes duty‑relevant information and that simply separating duties among agents is insufficient, as agents can lose sight of the overall goal. To address these issues, the authors propose Goal‑Aware Dynamic Multi‑Agent Collaboration (GAD), which uses an execution graph to organize subtasks, keeps each agent’s context focused on its specific goal, and dynamically adjusts task dependencies and information sharing based on execution evidence, with verification and recovery checks providing feedback for repair.
arXiv:2610.34238v1 Announce Type: cross
Abstract: In this paper, we introduce $\Delta\tau$-Bench, an executable agent benchmark that models the structural evolution of large tool ecosystems. In $\Del...
By Shuofei Qiao, Xuanguang Pan, Yijun Chen, Wendi Feng, Bin Wu, Runnan Fang, Yuqi Zhu, Shumin Deng, Emine Yilmaz
The paper introduces Goal-Aware Dynamic Multi-Agent Collaboration (GAD), a framework that assigns distinct duties to separate agents with individualized contexts to tackle long-horizon tasks. It employs a growing execution graph to structure subtasks and their dependencies, ensuring each agent retains the original instruction, task goal, and acceptance conditions. GAD dynamically adapts collaboration and information sharing, using verification and recovery checks to monitor subtask results and overall task completion, providing feedback for repair when checks fail.
By Xu Shen, Lingyong Yan, Shuaiqiang Wang, Jianmin Wu, Zhikai Chen, Jiliang Tang, Jie Ren
The paper introduces KNOWS, a benchmark for evaluating web agents that act as assistants by retrieving, synthesizing, and presenting information across complex, multi-step browser tasks. It outlines a task design rubric, evaluation protocol combining deterministic checks with LLM judgments, and reports that current agents achieve only modest success, with the best performing agent succeeding on less than 3% of tasks. The study highlights significant gaps in agents’ tool use, visual understanding, and long‑horizon reasoning.
By Alexander Gill, Md Farhan Ishmam, Xuyen Nguyen, Neha Bhat, Parker Henry DeYoung, Fateme Hashemi Chaleshtori, Nathan Stringham, Kenneth Marino, Ana Marasovi\'c
CoworkOS is a general‑purpose harness designed for long‑horizon real‑world automation, separating task strategy from execution management. Its three‑layer architecture allows direct execution or delegation to subagents, while a shared application layer lets humans and agents collaboratively edit documents, designs, and 3D scenes. The system incorporates hierarchical workspaces and persistent semantic memory to maintain continuity across agents and sessions, and demonstrates strong performance across 12 benchmarks and six application categories, outperforming leading agents like Codex and DeepSeek Harness.
By Jiajie Jin, Guanting Dong, Chengjun Pan, Xin Deng, Zhuohui Sheng, Guoqiang Wang, Tao Gui, Yutao Zhu, Yujia Chen, Shihong Yi, Binze Hu, Zhixiong Yang, Zhichao Sun, Rui Wang, Han Han, Mingyu Ma, Junhao Huang, Xiaotao Wang, Huicheng Jiang, Yuyang Hu, Xinyu Yang, Wanghan Xu, Yajie Yang, Zhecan Wang, Honglin Guo, Xiaoyu Xing, Xiaoqian Zhang, Yulun Zhu, Xiaoxi Li, Jiahang Lin, Shaofan Liu, Shihan Dou, Zhiheng Xi, Qi Zhang, Yu-Gang Jiang, See-Kiong Ng, Yang Zhang, Tat-Seng Chua, Ji-Rong Wen, Zhicheng Dou