--- title: "AWARE — paper by Qian et al. (2026) — summary and ideas" description: "The authors describe real-world sources such as web pages, PDFs and local files as noisy and low in useful content per token. 2 references." authors: ["Hongjin Qian", "Siqi Bao", "Zhao Cao", "Zheng Liu"] year: 2026 venue: "Findings of the Association for Computational Linguistics: ACL 2026" source: "https://aclanthology.org/2026.findings-acl.120/" doi: "10.18653/v1/2026.findings-acl.120" licence: "CC BY 4.0 (ACL Anthology)" licence_url: "https://creativecommons.org/licenses/by/4.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/qian-2026-aware-agentic-knowledge-warehousing-contextual/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/qian-2026-aware-agentic-knowledge-warehousing-contextual/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/24/) / AWARE: Agentic Knowledge Warehousing for Contextual Intelligence # AWARE: Agentic Knowledge Warehousing for Contextual Intelligence **Authors:** [Hongjin Qian](https://md.research.elamur.ai/free/en/authors/hongjin-qian/), [Siqi Bao](https://md.research.elamur.ai/free/en/authors/siqi-bao/), [Zhao Cao](https://md.research.elamur.ai/free/en/authors/zhao-cao/) and [Zheng Liu](https://md.research.elamur.ai/free/en/authors/zheng-liu/) · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: ACL 2026](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/) **Links:** [Publisher's page](https://aclanthology.org/2026.findings-acl.120/) · [PDF](https://aclanthology.org/2026.findings-acl.120.pdf) · [DOI 10.18653/v1/2026.findings-acl.120](https://doi.org/10.18653/v1/2026.findings-acl.120) · [OpenAlex](https://openalex.org/W7166875402) **Citations:** 0 citations (OpenAlex, 2026-10-14) ## Summary LLMs often fail on questions that need specialized or recent knowledge, and current fixes involve trade-offs. Classic RAG retrieves once and cannot follow chains of dependent facts. Tool-integrated reasoning agents keep all gathered evidence inside their context window, which limits how widely they can search. The authors describe real-world sources such as web pages, PDFs and local files as noisy and low in useful content per token. They propose AWARE, which treats retrieval as agentic knowledge construction. Offline, each document receives a short header describing its scope and structure, which allows cheap screening. Online, the agent plans a sequence of information intents and splits each into atomic sub-queries. It explores many threads in parallel and refines wherever dependencies remain unresolved. Evidence is then extracted and merged in map–reduce fashion outside the main reasoning loop. The result is a compact, step-ordered context that any LLM can use to answer. AWARE outperforms all baselines on GAIA, WebWalker and BrowseComp-Plus. It separates costly reasoning from bulk text processing, so standalone LLMs can handle long multi-hop search within fixed context budgets. ## Key points - The evaluation benchmarks are GAIA, WebWalker and BrowseComp-Plus, and the paper reports gains over every baseline. Exact scores are not in the excerpt provided. - The pipeline has four modules: - offline document structuring with headers; - multi-threaded exploration with targeted refinement; - map–reduce evidence integration; - task-aware contextualization into LLM-ready input. - Header-level screening discards close to 90% of irrelevant retrieved pages before detailed processing. - Raising exploration depth from 1 to 5 improves results, after which performance fluctuates as evidence saturates. Deeper search also reduces the number of intents needed. - In a GAIA-style case study (answer: "Mice"), one intent used 4 atomic queries, retrieved 36 pages and browsed 13. Reasoning used about 8.9K tokens versus about 227.2K for bulk processing. This shows that a strong central model can be paired with lightweight auxiliary models. *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* ## Institutions - [Hong Kong University of Science and Technology](https://md.research.elamur.ai/free/en/universities/hong-kong-university-of-science-and-technology/) — University, Hong Kong, China · 170 works · 26,341 citations - [Renmin University of China](https://md.research.elamur.ai/free/en/universities/renmin-university-of-china/) — University, Beijing, China · 139 works · 17,752 citations - [Hong Kong Polytechnic University](https://md.research.elamur.ai/free/en/universities/hong-kong-polytechnic-university/) — University, Hong Kong, China · 106 works · 5,190 citations - [Beijing Academy of Artificial Intelligence](https://md.research.elamur.ai/free/en/labs/beijing-academy-of-artificial-intelligence/) — Research institute, Beijing, China · 46 works · 8,682 citations 📚 Shelves (6): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 3,486 works · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,730 works 🧭 Topics (1): [🧮 Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/) · 1,685 works ## Cite Cite as: Hongjin Qian, Siqi Bao, Zhao Cao and Zheng Liu. 2026. AWARE: Agentic Knowledge Warehousing for Contextual Intelligence. Findings of the Association for Computational Linguistics: ACL 2026. The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{qian2026aware, title = {{AWARE: Agentic Knowledge Warehousing for Contextual Intelligence}}, author = {Hongjin Qian, Siqi Bao, Zhao Cao and Zheng Liu}, booktitle = {Findings of the Association for Computational Linguistics: ACL 2026}, year = {2026}, doi = {10.18653/v1/2026.findings-acl.120}, url = {https://doi.org/10.18653/v1/2026.findings-acl.120} } ``` - [← previous AvarLab: An Integrated Digital Ecosystem for Avar, a Morphologically Rich Low-Resource Language](https://md.research.elamur.ai/free/en/papers/zagidov-2026-avarlab-integrated-digital-ecosystem-avar/) - [next → AyahVerse at AbjadGenEval Shared Task: Monolingual Precision and Cross-Lingual Analysis in Perso-Arabic AI Detection](https://md.research.elamur.ai/free/en/papers/nawaz-2026-ayahverse-abjadgeneval-shared-task-monolingual/) - [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/24/) ## References 2 references, 1 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. This work was supported by National Natural Science Foundation of China No. 62502049. [find](https://scholar.google.com/scholar?q=This+work+was+supported+by+National+Natural+Science+Foundation+of+China+No%2E+62502049%2E) 2. Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi. 2024. [Self-rag: Learning to retrieve, generate, and critique through self-reflection](https://md.research.elamur.ai/free/en/papers/asai-2023-self-rag-learning-retrieve-generate/). In The Twelfth International Conference on Learning Representations. \#\# Limitations Although AWARE demonstrates strong performance across div… *Updated 1 November 2026*