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
arXiv:2606. 04455v1 Announce Type: new Abstract: Current AI benchmarks evaluate agents on task execution within human-designed workflows.
By Xinyu Lu, Tianshu Wang, Pengbo Wang, zujie wen, Zhiqiang Zhang, Jun Zhou, Boxi Cao, Yaojie Lu, Hongyu Lin, Xianpei Han, Le Sun
Agentick is a unified benchmark for sequential decision‑making agents that evaluates RL, LLM, VLM, hybrid, and human agents on 37 procedurally generated tasks across six capability categories, four difficulty levels, and five observation modalities via a single Gymnasium‑compatible interface. It includes a Coding API, oracle reference policies, pre‑built SFT datasets, a composable agent harness, and a live leaderboard. An evaluation of 27 configurations and over 90,000 episodes shows no single approach dominates, with GPT‑5 mini leading overall, PPO excelling in planning and multi‑agent tasks, and the reasoning harness boosting LLM performance by 3‑10×, while ASCII observations outperform natural language.
By Roger Creus Castanyer, Pablo Samuel Castro, Glen Berseth
The paper introduces AIDE^2, an AI research agent that recursively improves its own code by proposing, benchmarking, and selecting modifications. Over an eight‑day autonomous run, it achieved seven successive improvements—including new search policies and memory mechanisms—that transferred to four held‑out benchmarks in machine learning, algorithm engineering, and weather forecasting. The agent’s best version matched or outperformed a top human‑engineered production research agent and also reduced reward‑hacking rates, despite never optimizing for that metric.
By Dhruv Srikanth, Bingchen Zhao, Dixing Xu, Yuxiang Wu, Zhengyao Jiang
arXiv:2609. 37968v1 Announce Type: new Abstract: Advances in the coding capabilities of LLM agents allow them to inspect and modify their own instructions, tools, and execution procedures.
By Jungwoo Yang, In Jin Kong, Yohan Jo
RSIGym is a new agent-native research environment built on Everything as a Service (EaaS) that exposes training, inference, rollout, evaluation, and sandbox execution through reusable services. It supports shared budget and permission controls for Data, Harness, and Joint improvement tracks, allowing agents to investigate individual interventions and jointly optimize data, training settings, and execution harnesses within the same environment. Using RSIGym, the Opus 5 model achieved the highest RSI-Index of 0.4809 across five benchmarks, improving performance on software engineering, terminal interaction, mathematics, scientific reasoning, and skill-based tasks.
By Fanqing Meng, Lingxiao Du, Haocheng Lu, Qiguang Chen, Ziqi Zhao, Zijian Wu, Jiayuan Zhuo, Mengkang Hu, Michael Qizhe Shieh