VisDocAgentBench is a closed‑corpus benchmark that evaluates static versus agentic retrieval for visually rich documents, using 2,375 pages from 100 documents and 120 queries that span direct, one‑bridge, and two‑bridge evidence structures. The benchmark includes semantic, relational, and visual queries, full‑document review, and hard‑negative validation. Results show that a strong visual retriever performs well on direct items but poorly on two‑bridge items, while agents improve performance, especially when using visual retrieval and iterative search capabilities.
By Lexiang Hu, Yanzhao Zhang, Mingxin Li, Dingkun Long, Yikang Li, Fuwei Zhang, Yisen Wang, Zhouchen Lin
arXiv:2609.37226v1 Announce Type: cross
Abstract: Answering questions and completing tasks over large document collections often requires connecting evidence spread across multiple documents, such as...
By Soyeong Jeong, Sujay Kumar Jauhar, Sung Ju Hwang, Andrew Joohun Nam
arXiv:2609.14412v1 Announce Type: new
Abstract: Deep research agents answer complex questions through iterative loops of searching, reading, and reasoning. Recent work on reasoning-intensive benchmar...
By Radin Hamidi Rad, Amin Bigdeli, Negar Arabzadeh, Sajad Ebrahimi, Charles L. A. Clarke, Benjamin C. M. Fung, Ebrahim Bagheri
arXiv:2610.17827v1 Announce Type: new
Abstract: Existing approaches to training and evaluating search agents focus heavily on final-answer quality, largely neglecting how generated answers map back t...
By Haochen Zhao, Minsheng Hao, Zheng Li, Yifan Li, Zikang Liu, Bowen Qin, Yuhao Cheng, Chuang Fan, Haosheng Zou, Jeff Chen, Sujian Li
MOSAIC is a training‑free framework that adapts Graph Retrieval‑Augmented Generation (GraphRAG) to each query by converting query‑specific evidence needs into a bounded policy over seed selection, traversal, stopping, and evidence selection. It keeps the corpus graph, indexes, scoring, grounding, and answer generation shared, while an LLM analyzer tailors the exploration strategy per query. On GraphRAG‑Bench, MOSAIC improves answer correctness by over 5 points on Medical and 4 points on Novel, achieves high evidence recall and context relevancy, and reduces path and evidence evaluations compared to fixed policies.
By EunKyeong Lee, Kyeong-Jin Oh, Jinwon Kim, Hye Woo Lee, Minsang Song, Hyeongjun Jang, Junyoung Youn
arXiv:2609.39026v1 Announce Type: new
Abstract: Deep Research agents synthesize evidence into cited reports, yet a well-cited report can still reach a misleading conclusion. Citation correctness chec...
By Shuyao Xiao, Shengling Wang, Xuan Chen, Ke Chao, Ming Cui, Feifei Qian, Chaoyang Mei, Fanlin Meng, Lulu Wang, Ziming Yu, Junxi Yin
The paper introduces AtlasNav, a persistent multi‑view corpus‑navigation framework that organizes a corpus into a Corpus Atlas, enabling large‑language‑model agents to navigate efficiently under finite interaction budgets. AtlasNav reduces online inference cost by 30.21% and achieves 92.05% strict accuracy on BrowseComp‑Plus, while earlier and more rapidly realizing required evidence compared to dynamic‑workspace methods. The approach also transfers well to other corpora such as PhantomWiki and heterogeneous enterprise knowledge bases, demonstrating that effective agentic search relies on both accessible evidence and a reusable corpus representation.
By Hongyu Guo, Zhiyu Zheng, Zhao Cao
arXiv:2608.24764v2 Announce Type: replace
Abstract: As language-model agents become more capable of iterative search, corpus access is shifting from retrieval toward interaction. Agents can explore t...
By Hongyu Guo, Zhiyu Zheng, Minghao Hu, Shuai Lei, Zhunchen Luo, Chao Ma, Yunbo Cao, Zhao Cao
LongHarness is a model‑agnostic harness that explicitly manages the interaction between acquired evidence and evolving conclusions for long‑context reasoning over corpora larger than a model’s context window. Its Evidence‑Conclusion Coevolution mechanism uses unresolved conclusions to steer evidence retrieval, while new evidence refines those conclusions, and its Evidence Lifecycle Management keeps evidence current and traceable. Evaluations on OfficeQA Pro, AA‑LCR, and LongBench v2 show substantial performance gains over direct reasoning and state‑of‑the‑art agent harnesses, with GLM‑5.3‑Flash exact match improving from 15.8% to 60.2% on V1 and from 4.4% to 61.1% on V2.
By Songtao Huang, Zhijie Zhong, Xiaohan He, Shuaiyu Zhang, Zhiyin Yu, Li Kang, Heng Zhou, Yutao Fan, Xiangchao Yan, Bo Zhang, Shiyang Feng
PathAnchor is a new scientific reasoning system that uses path-structured evidence workspaces instead of independent passages or concepts. It retrieves source-linked Material‑Sensor‑Signal‑System trajectories that preserve role, direction, and supporting evidence, and a controller uses read‑only tools to search, trace, and open exact evidence before producing a claim‑cited answer. In evaluations on 120 flexible‑sensor questions, PathAnchor achieved an 82.6% score, outperformed six other systems, and improved source recall, citation completeness, and reduced tool calls compared to unordered concept graphs.
By Qiuhui Chen, Jiafan Lu, Shuaimin Tang, Tao Dai, Suyuan Wang, Chenrui Ji, Zhenglei Zhou, Weimin Zhong
arXiv:2605. 12887v2 Announce Type: replace-cross Abstract: Web-enabled LLM agents are changing how online information influences search outcomes.
By Hengwei Ye, Jiasheng Mao, Zhenhan Guan, Zheng Tian
Scientific datasets are commonly organized as hierarchical repositories containing heterogeneous and interdependent files, making their inspection, integration, and analysis labor-intensive and reliant on domain expertise. Although large language model (LLM) agents have advanced substantially in planning, reasoning, and tool use, existing research has largely overlooked their ability to interact with real scientific data assets through executable environments.