无需训练数据即可自我进化的搜索代理，突破传统学习范式，实现自主迭代优化。
arXiv:2601.07055v2 Announce Type: replace Abstract: As high-quality data becomes increasingly difficult to obtain, self-evolution without curated trai…
融合轨迹感知与证据生态，让LLM搜索代理更可信、更高效
arXiv:2605.12887v2 Announce Type: replace-cross Abstract: Web-enabled LLM agents are changing how online information influences search outcomes. Exist…
研究揭示LLM搜索代理易受网页内容操控影响，测量“背书漏洞”的严重性，关乎AI安全底线。
arXiv:2606.16821v1 Announce Type: new Abstract: Large language model (LLM)-based search agents synthesize open-web content into actionable recommendat…
开源的日常搜索评估基准，专测AI搜索代理的综合信息处理能力。
arXiv:2606.12871v1 Announce Type: new Abstract: Search Agents (SAs) typically leverage large language models (LLMs) to support complex information-see…
开源AI搜索代理Harness-1通过优化记忆机制，在信息回忆任务上击败GPT-5.4，展现开源模型的潜力。
A joint research collaboration between researchers at the University of Illinois at Urbana-Champaign (UIUC), UC Berkeley, and the open source AI-nativ…
提出ARBOR框架，用可复用评分缓冲为搜索代理提供在线过程奖励，显著提升推理与搜索效率。
arXiv:2606.03239v1 Announce Type: new Abstract: LLM-based search agents are trained predominantly with outcome-only reward, leaving the search process…
提出信用衰减特权反馈方法，引导搜索代理在硬问题上突破成功轨迹稀疏瓶颈
arXiv:2606.01830v1 Announce Type: new Abstract: Recent LLM search agents use reinforcement learning with verifiable rewards (RLVR) to learn search-aug…
提出COMPASS框架，用认知MCTS引导过程对齐，让搜索代理更安全可控
arXiv:2605.30838v1 Announce Type: new Abstract: LLM-powered search agents enable multi-step reasoning and tool use. However, these capabilities introd…
自动化红队测试框架，专攻LLM搜索代理的安全漏洞，已被ICML 2026接收。
arXiv:2509.23694v5 Announce Type: replace Abstract: Search agents connect LLMs to the Internet, enabling them to access broader and more up-to-date in…
提出GrepSeek方法训练LLM搜索代理直接与语料库交互，摆脱传统检索器限制，提升知识密集型任务效率。
arXiv:2605.29307v1 Announce Type: cross Abstract: Large Language Model (LLM) search agents have shown strong promise for knowledge-intensive language …