AgentPProf is a new semantic profiler designed for long‑horizon AI agents that aggregates agent trajectories into pprof‑compatible profiles, enabling flame‑graph visualization and hierarchical attribution of tasks and subtasks. It introduces a semantic operation stack model and recursive operation segmentation to replace traditional call‑stack profiling, addressing the challenge of profiling agent intent rather than code paths. In evaluations, AgentPProf achieves high F1 scores against human annotations and significantly improves problem‑localization metrics, demonstrating its effectiveness in attributing resources, locating issues, and optimizing token cost.
By Yusheng Zheng, Chaokun Chang, Yu Mao, Tianyuan Wu, Yuxi Huang, Tao Ma, Wenan Mao, Shuyi Cheng, Andi Quinn, Wei Wang
arXiv:2605. 12925v3 Announce Type: replace-cross Abstract: Evaluation of software engineering (SWE) agents is dominated by a binary signal: whether the final patch passes the tests.
By Priyam Sahoo, Gaurav Mittal, Xiaomin Li, Shengjie Ma, Benjamin Steenhoek, Pingping Lin, Yu Hu
arXiv:2606. 08500v1 Announce Type: cross Abstract: Software engineering agents (SWE agents) increasingly work through tool-mediated trajectories in real repositories, yet their behavior remains difficult to characterize in concrete, observable terms.
By Zhengyi Zhuo, Yan Liu
arXiv:2606. 30573v1 Announce Type: new Abstract: We introduce SWE-Interact, a new testbed for evaluating coding agents on multi-turn, interactive, user-driven software engineering tasks.
By Mohit Raghavendra, Anisha Gunjal, Aakash Sabharwal, Yunzhong He
arXiv:2603. 14465v2 Announce Type: replace Abstract: While Large Language Models (LLMs) have evolved into tool-using agents, they remain brittle in long-horizon interactions.
By Shengda Fan, Xuyan Ye, Yupeng Huo, Zhi-Yuan Chen, Yiju Guo, Shenzhi Yang, Wenkai Yang, Shuqi Ye, Jingwen Chen, Haotian Chen, Xin Cong, Yankai Lin
The paper investigates what makes software issue resolution tasks difficult for agents by proposing a measurement framework and conducting a large‑scale empirical study on the CoderForge‑Preview dataset. It extracts static features from task patches, repositories, and prompts, and uses ensemble methods, SHAP attribution, and effect size analysis to predict task outcomes. The study finds that task difficulty is largely predictable from static features (AU C = 0.863), driven mainly by patch fragmentation and repository scale, with prompt linguistic features contributing for mid‑band tasks, suggesting a layered difficulty structure.
By Ebtesam Al-Haque, Brittany Johnson
The paper presents EvalAgent, an AI assistant that automates agent evaluation by encoding domain expertise into evaluation skills such as procedural instructions, reusable code, and dynamic API retrieval. EvalAgent constructs a trace-based pipeline that outputs metrics, executable code, and reports, and is evaluated using a new meta-evaluation framework and AgentEvalBench. Results show that EvalAgent improves the Eval@1 metric from 17.5% to 65% and receives 79.5% human expert preference, while ablation studies confirm the importance of evaluation skills.
By Kang Zhou, Sangmin Woo, Haibo Ding, Kiran Ramnath, Subramanian Chidambaram, Aosong Feng, Vinayak Arannil, Muhyun Kim, Ishan Singh, Darren Wang, Zhichao Xu, Megha Gandhi, Nirmal Prabhu, Soumya Smruti Mishra, Smeet Dhakecha, Vivek Singh, Gouri Pandeshwar, Lin Lee Cheong
Agent skills are the de facto mechanism for extending LLM agents with reusable guidance. A skill can shape the agent's task execution, including planning, tool use, problem-solving, and validation.
arXiv:2608. 08570v1 Announce Type: new Abstract: Rejection sampling fine-tuning (RFT) is widely used to train code agents by generating trajectories on verifiable software engineering tasks, retaining those that pass the tests, and fine-tuning on the successful rollouts.
By Dongyi Lv, Fushun E, Aichen Cai, Liang Huang, Ya Zhang, Qiuyu Ding, Canhui Wu, Zhi Wang, Yuesong Zhang, Jiaqi Wang, Nan Duan
arXiv:2608. 20319v1 Announce Type: cross Abstract: Naturalistic computer-use traces, passively recorded screenshots and mouse or keyboard actions, are a valuable resource for deriving symbolic, auditable, and reusable models of how everyday work is done.
By Yucheng Jiang, Zora Zhiruo Wang, Ruishi Chen, Diyi Yang
arXiv:2609.01271v1 Announce Type: cross
Abstract: Agentic software engineering benchmarks are typically summarized by nominal category labels such as "bug fix" or "feature implementation," yet benchm...
By Radin Shayanfar, Keheliya Gallaba, Ahmed E. Hassan
arXiv:2607. 10059v1 Announce Type: new Abstract: Agent systems based on large language models (LLMs) are increasingly deployed for autonomous tasks, yet existing evaluations mostly focus on task success rather than whether agents know when to abstain.
By Xun Liu, Yi Evie Zhang, Vira Kasprova, Parisa Rabbani, Pardis Sadat Zahraei, Tianyu Zhang, Ali Ebrahimpour-Boroojeny, Varun Chandrasekaran