OS-Marathon is a new benchmark that tests computer‑use agents on vast‑horizon, repetitive tasks, covering 100 tasks across five scenarios and ten domains. The study shows that current state‑of‑the‑art agents perform poorly on these tasks, and that simply decomposing workflows into subtasks does not solve the problem. Introducing a cost‑friendly personalization method called GraphDemo, which adapts agents from a single human demonstration, improves performance, highlighting the value of human guidance for these challenging tasks.
By Jing Wu, Wenjie Ai, Daphne Barretto, Yiye Chen, Qingyu Chen, Yuhang He, Pranit Chawla, Nicholas Gyd\'e, Yanan Jian, Vibhav Vineet
arXiv:2603. 17216v2 Announce Type: replace Abstract: With the advent of AI agents, automated scientific discovery is becoming an increasingly plausible goal.
By Ziyang Cai, Amir Saeidi, Harkirat Behl
AlgoEvo introduces a unified agentic framework for automated algorithm discovery that replaces rigid search pipelines with an interactive, knowledge‑accumulating process. An autonomous agent inspects, diagnoses, and edits code using runtime feedback, while a design skill hub decouples paradigm‑specific knowledge from the core engine, enabling a single workflow to handle single‑objective, multi‑objective, and multi‑component design tasks. The hierarchical experience mechanism organizes search trajectories into a task‑level tree, guiding exploration and consolidating cross‑task patterns into reusable skills, resulting in performance that matches or surpasses specialized methods with fewer evaluations and reduced token consumption.
By Junhao Qiu, Qinglong Hu, Xialiang Tong, Mingxuan Yuan, Liyong Lin, Qingfu Zhang
The paper introduces Librarian Agents, a framework that trains large language models to proactively curate long-context workspaces by reorganizing raw documents into a hierarchical filesystem of synthetic files and reference links. This builder agent, optimized via reinforcement learning, aims to maximize downstream answering accuracy by anticipating future queries rather than reacting to them. Experiments show that Librarian Agents outperform leading retrieval and precomputation methods, achieving a 33‑point accuracy gain on BrowseComp‑Plus and a 31‑point improvement on BRIGHT in zero‑shot settings.
By Anikait Singh, Teresa Zhang, Yoonho Lee, Roshen Sanjay Nair, Aviral Kumar, Chelsea Finn
arXiv:2607. 21461v1 Announce Type: new Abstract: Deep research requires agents to find answers that jointly satisfy multiple constraints.
By Shuqi Lu, Chaofan Li, Kun Luo, Zhang Zhang, Hui Wang, Hongwang Xiao, Zheng Liu, Lei Xiong, Jiahao Wang, Sen Wang, Xiyan Jiang, Wanli Li, Yuyang Hu, Hongjin Qian, Bingyu Yan, Ziyi Xia, Yingxia Shao, Kang Liu, Zhicheng Dou, Di He, Chaozhuo Li, Qiwei Ye, Zhongyuan Wang, Zheng Liu
arXiv:2608. 04682v1 Announce Type: cross Abstract: Coding agents powered by large language models (LLMs) are increasingly adopted in software engineering (SWE) scenarios, capable of fixing a specific bug in large-scale codebase.
By Haobin Li, Ping Deng, Weizhong Qian, Liang Jiang, Zhenyu Huang, Mouxing Yang, Xi Peng
arXiv:2605. 08678v3 Announce Type: replace Abstract: Modern AI progress has been driven by ML methods that are generalizable across settings and scalable to larger regimes.
By Bohan Lyu, Yucheng Yang, Siqiao Huang, Jiaru Zhang, Qixin Xu, Xinghan Li, Xinyang Han, Yicheng Zhang, Huaqing Zhang, Runhan Huang, Kaicheng Yang, Zitao Chen, Wentao Guo, Junlin Yang, Xinyue Ai, Wenhao Chai, Yadi Cao, Ziran Yang, Kun Wang, Dapeng Jiang, Huan-ang Gao, Shange Tang, Chengshuai Shi, Simon S. Du, Max Simchowitz, Jiantao Jiao, Dawn Song, Chi Jin
arXiv:2606. 30704v1 Announce Type: cross Abstract: Large language models (LLMs) excel across a wide range of tasks, yet their instance-specific solutions often lack the structural consistency needed for reliable deployment.
By Gan Luo, Zihan Qin, Bin Dong, Wotao Yin
The paper introduces collaborative learning for large language models, where a single large model is replaced by smaller, heterogeneous models—called model slices—under a comparable parameter budget. By enabling prior reasoning to be reassessed across different model parameterizations and employing pyramid supervision that blends protocol distillation with step‑level supervision, the authors refine reasoning and interaction decisions during collaboration. Experiments on multi‑hop question answering, mathematical reasoning, code generation, and open‑ended constrained generation show that the trained heterogeneous models match or surpass the performance of the original large model and established multi‑agent baselines, while also achieving higher inference efficiency and exhibiting task‑specific collaboration patterns.
By Yuheng Wang, Runde Yang, Zhuohan Bao, Qiran Zhang, Huatao Li, Yiyang Zheng, Lin Wu, Jingru Fan, Shu Yao, Yihan Li, Zhi Li, Chen Qian
The paper introduces Proof-of-Use (PoU), a reinforcement learning framework designed to prevent tool‑call hacking in deep research agents. PoU enforces evidence grounding by requiring agents to cite normalized evidence identifiers and uses a multi‑objective reward system that includes progressive process rewards, an answer‑support alignment reward, and a curriculum‑style adaptive reward mixing. Experiments demonstrate that PoU effectively mitigates tool‑call hacking and promotes robust, adaptive tool usage even under domain and tool shifts.
By Shengjie Ma, Chenlong Deng, Jiaxin Mao, Jiadeng Huang, Teng Wang, Junjie Wu, Changwang Zhang, Jun wang
ASTRA-bench is a benchmark designed to evaluate AI agents’ reasoning and action planning in the presence of evolving personal context and an interactive toolbox. It generates 2,413 scenarios across four protagonists, incorporating longitudinal life events and varying levels of referential, functional, and informational complexity. Evaluation of leading models shows a marked drop in performance under high-complexity conditions, highlighting argument generation as a key bottleneck and exposing limitations in grounding reasoning within messy personal data.
By Zidi Xiu, David Q. Sun, Kevin Cheng, Maitrik Patel, Josh Date, Yizhe Zhang, Jiarui Lu, Omar Attia, Raviteja Vemulapalli, Oncel Tuzel, Meng Cao, Samy Bengio
arXiv:2605. 21850v2 Announce Type: replace-cross Abstract: Recent development of agents has renewed demand for long-context reasoning capacity of LLMs.
By Qisheng Su, Zhen Fang, Shiting Huang, Yu Zeng, Yiming Zhao, Kou Shi, Ziao Zhang, Lin Chen, Zehui Chen, Lijun Wu, Feng Zhao