HarnessEvolve is a self‑evolving framework that improves agent harnesses—prompts, skills, tools, and execution logic—by learning from reference trajectories. It separates execution, evaluation, optimization, and gating into independent modules, addressing credit assignment failure, shortcut learning, and catastrophic forgetting. The approach uses reference trajectories to extract error signals, applies quality and performance gates to candidate updates, and validates updates on held‑out data, consistently outperforming state‑of‑the‑art baselines across diverse benchmarks.
By Wen Jiang, Mingmin Chu, Yimeng Tian, Qianxin Zhang, Haofei Yang, Rui Yang, Yang Liu, Tao Lv, Fangming Li
arXiv:2608. 12851v1 Announce Type: new Abstract: Self-improving LLM agents convert successful trajectories into persistent cross-task state.
By Xutao Mao, Liangjie Zhao, Xiang Zheng, Cong Wang
arXiv:2606. 05684v1 Announce Type: new Abstract: A central challenge for language agents is utilizing past experience to adapt to dynamic test-time conditions.
By Yunxiang Zhang, Yiheng Li, Ali Payani, Lu Wang
Experience-driven self-evolution is critical for large language model (LLM) agents to improve through open-world interaction. However, existing experience learning methods mostly rely on single-agent loops, where the same agent executes tasks, summarizes outcomes, and determines memory content.
arXiv:2606. 06054v1 Announce Type: new Abstract: Personal AI agents increasingly rely on long-term memory to provide persistent personalization across sessions.
By Jiawen Zhang, Kejia Chen, Jiachen Ma, Yangfan Hu, Lipeng He, Yechao Zhang, Jian Liu, Xiaohu Yang, Tianwei Zhang, Ruoxi Jia
SafeCoEvo is a test‑time framework that co‑evolves safety harnesses and guards for large language model agents. It uses a short‑term S‑Harness to quickly externalize recent runtime experience into explicit safety knowledge, and a long‑term GuardVPO to internalize accumulated experience into parametric risk‑judgment capabilities. This dual adaptation improves safety and task success, reducing unsafe outcomes by 10.05% and increasing task success by 12.15% over the strongest baseline.
By Yu Cheng, Yongkang Hu, Shuaijie Ma, Zhihang Lin, Weicheng Meng, Jingyang Qiao, Jiuan Zhou, Yushuo Zhang, Yihang Chen, Weilin Luo, Kun Shao, Dong Li, Zhizhong Zhang, Yuan Xie, Zhaoxia Yin
arXiv:2608. 12428v1 Announce Type: new Abstract: Memory is a core component of AI agents, enabling them to accumulate experience, maintain personalization, and adapt over long-term interactions.
By Kaichao Liang, Yuqi Cui, Hao Kong, Xinyuan Huang, Guohaotian Hou, Qingcan Kang, Liang Chen, Yiyang Yin, Ke Ye, Jiaquan Guo, Da Chen, Lingan Zeng, Yixing Peng, Rong Yao, Shixiong Kai, Mingxuan Yuan
arXiv:2609.08832v1 Announce Type: new
Abstract: Large language model (LLM)-powered agents can be accurate on average yet unreliable in production, a discrepancy that has been observed but remains lar...
By Evelyn Duesterwald, Benjamin Elder, Lilian Ngweta, Shashanka Ubaru, Malgorzata Zimon
The paper re‑evaluates memory‑based self‑improving agents by adding multiple runs to measure variance and by randomizing task order. It finds that agent performance is noisy in complex, multi‑step environments and that improvement depends heavily on the sequence of tasks, revealing a hidden curriculum effect. The authors suggest that underspecification of tasks and environments contributes to this fragility and demonstrate that adding detailed rubrics and feedback can partially mitigate performance drops, though gaps remain.
By Qinyuan Ye, Yu Li, Yada Pruksachatkun, Jiaxin Zhang, Chien-Sheng Wu
arXiv:2605.09278v2 Announce Type: replace
Abstract: Multi-agent debate (MAD) systems increasingly rely on shared memory to support long-horizon reasoning, but this convenience opens a critical vulner...
By Yuqiao Meng, Luoxi Tang, Sakshi Sunil Narvekar, Rupali Rajendra Vaje, Yingxue Zhang, Muchao Ye, Zhaohan Xi
MemoryArena is a new evaluation gym that benchmarks agent memory in interdependent multi‑session tasks. Unlike prior benchmarks that test memorization or single‑session action in isolation, MemoryArena requires agents to acquire memory while interacting with the environment and then use that memory to guide future decisions across a range of tasks such as web navigation, planning, information search, and formal reasoning. The benchmark reveals that agents excelling on existing long‑context memory tests perform poorly here, highlighting a gap in current memory evaluation methods.
By Zexue He, Yu Wang, Churan Zhi, Yuanzhe Hu, Tzu-Ping Chen, Lang Yin, Ze Chen, Tong Arthur Wu, Siru Ouyang, Zihan Wang, Jiaxin Pei, Julian McAuley, Yejin Choi, Alex Pentland
arXiv:2607. 08716v1 Announce Type: new Abstract: In long-horizon tasks, decision-relevant state is often scattered across an expanding trajectory, while the action agent must surface it and act.
By Yifan Wu, Lizhu Zhang, Yuhang Zhou, Mingyi Wang, Bo Peng, Serena Li, Xiangjun Fan, Zhuokai Zhao