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
The paper introduces Gated-Memory Routing, a method for efficient collaboration in multi‑agent large language model systems. It uses a learned execution memory with write and retrieval gates to keep only non‑redundant reasoning steps, and an adaptive halting controller to stop execution when enough evidence is gathered. Experiments on five reasoning and code‑generation benchmarks show the approach achieves higher accuracy and reduces inference cost by 31.9% compared to the strongest baseline.
By Rakibul Hasan Rajib, Mengxing Zheng, Qian Lou
The paper introduces AMBER, an append‑only memory framework for language‑model agents that interact over long horizons. AMBER lets agents jointly learn to reason, act, and write free‑form memory, guaranteeing retention by construction and enabling end‑to‑end reinforcement learning without extensive curated data. Experiments on WebArena Lite show AMBER outperforms overwrite‑based memory by 4.09 percentage points in average success and improves task completion rates in repeated runs.
By Chinmay Savadikar, Zhaoyu Zhang, Mingyu Zhao, Shuang Xie, Han Li, Tianfu Wu, Lingyun Wang
arXiv:2506. 01952v2 Announce Type: replace-cross Abstract: Powered by large language models (LLMs), web browsing agents operate graphical user interfaces in a human-like manner, offering a transparent and general framework for automating web-based tasks.
By Atsuyuki Miyai, Zaiying Zhao, Kazuki Egashira, Atsuki Sato, Tatsumi Sunada, Shota Onohara, Hiromasa Yamanishi, Mashiro Toyooka, Kunato Nishina, Ryoma Maeda, Kiyoharu Aizawa, Toshihiko Yamasaki
arXiv:2511. 12997v2 Announce Type: replace Abstract: Multimodal LLM-powered agents have recently demonstrated impressive capabilities in web navigation, enabling agents to complete complex browsing tasks across diverse domains.
By Genglin Liu, Shijie Geng, Sha Li, Hejie Cui, Sarah Zhang, Xin Liu, Tianyi Liu
Building capable visual web agents requires long-horizon reasoning, precise grounding, and robust interaction with dynamic real-world websites. Despite rapid progress, the strongest systems remain largely proprietary, while open agents still depend heavily on supervised post-training over large collections of curated web trajectories.
arXiv:2606. 02031v1 Announce Type: cross Abstract: Building capable visual web agents requires long-horizon reasoning, precise grounding, and robust interaction with dynamic real-world websites.
By Rui Yang, Qianhui Wu, Yuxi Chen, Hao Bai, Wenlin Yao, Hao Cheng, Baolin Peng, Huan Zhang, Tong Zhang, Jianfeng Gao
arXiv:2610.08155v1 Announce Type: cross
Abstract: Large language model (LLM)-based multi-agent systems (MAS) have become a promising paradigm for complex information-seeking and reasoning tasks by en...
By Zihan Zhou, Xinzhe Hu, Hanxu Yang, Liangjian Wen, Zhao Kang
arXiv:2603.05294v3 Announce Type: replace
Abstract: Existing LLM-based web agents struggle on complex, long-horizon tasks due to limited in-context memory, weak planning abilities, and greedy behavio...
By ELita Lobo, Xu Chen, Jingjing Meng, Nan Xi, Yang Jiao, Chirag Agarwal, Yair Zick, Yan Gao
arXiv:2606. 02871v1 Announce Type: cross Abstract: Large reasoning models improve performance by generating extended chain-of-thought (CoT) reasoning, but this behavior becomes inefficient when applied to LLM agents.
By Dongwon Jung, Peng Shi, Yi Zhang, Junshan Zhang, Muhao Chen
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
Deep search requires agents to answer complex questions through multi-step web search, browsing, evidence comparison, and synthesis. A central challenge is deciding how to search when several directions look plausible but only some will later lead to reliable evidence.