Organizations: Fudan University · Zhejiang University · Shanghai Qiji Zhifeng Co., Ltd.
Abstract
Large language models are increasingly deployed as agents that reason over documents rather than answer from parametric knowledge. We study archive-grounded reasoning: locating sparse evidence across a large, messy collection of workplace files, reconciling inconsistent terminology, units, and time conventions, and computing an answer. Existing benchmarks address only parts of this setting and none jointly stresses archive-groundedness, agentic exploration, and cross-domain coverage. We introduce Agora, a benchmark pairing 362 questions with eight domain collections of 9,664 authentic documents and 372M tokens, far exceeding any model's context window, so agents must explore deliberately rather than scan exhaustively. Agora is built by an agentic pipeline combining cross-document task synthesis, leakage-preventing obfuscation, and difficulty filtering. Evaluating eight models, we find the task far from solved: even the strongest reaches only 59.4% accuracy, with notable variation across domains.
We present AgenticRAG, a practical agentic harness for retrieval and analysis over enterprise knowledge bases. Standard RAG pipelines place significant burden of grounding on the search stack, constraining the language model to a fixed candidate set chosen deep in the retrieval process. Our approach reduces this overdependence by layering a lightweight harness on top of existing enterprise search infrastructure, equipping a reasoning LLM with search, find, open, and summarize tools enabling the model to iteratively retrieve information, navigate within documents, and analyze evidence autonomously. On three open benchmarks we observe substantial gains: 49.6% recall@1 on BRIGHT (+21.8 pp over the best embedding baseline), 0.96 factuality on WixQA (+13% relative improvement), and 92% answer correctness on FinanceBench--within 2 pp of oracle access to true evidence. Ablation studies show that the most significant factor is the shift from single-shot retrieval to agentic tool use (5.9× improvement), while multi-query search and in-document navigation contribute to both quality and efficiency. We present various design choices in our agentic harness that were informed by pre-production deployments. Our results demonstrate its suitability for real-world enterprise production environments.
Agentic retrieval-augmented generation systems can produce answers that appear grounded while failing at the evidence, tool-contract, authorization, or session-state layer. We introduce LayerRAG-Bench, a controlled cross-layer reliability benchmark with 8 enterprise domains, 240 tasks, 9 fault scenarios, 2 contract modes, and 38,880 live task-level records across nine models from OpenAI, Anthropic, and Gemini. Schema normalization raises schema-drift success from 0.000 to 0.913, but stale evidence, missing tool output, denied permissions, and wrong-session context are not recovered by schema normalization. Groundedness-only evaluation also produces substantial false positives under stale and wrong-session evidence. These results support a layer-specific evaluation principle: a reliability intervention should be credited for repairing its target layer without being mistaken for a universal fix.
Evaluating whether Multimodal Large Language Models can produce trustworthy, verifiable reasoning over long, visually rich documents requires evaluation beyond end-to-end answer accuracy. We introduce DocScope, a benchmark that formulates long-document QA as a structured reasoning trajectory prediction problem: given a complete PDF document and a question, the model outputs evidence pages, supporting evidence regions, relevant factual statements, and a final answer. We design a four-stage evaluation protocol -- Page Localization, Region Grounding, Fact Extraction, and Answer Verification -- that audits each level of the trajectory independently through inter-stage decoupling, with all judges selected and calibrated via human alignment studies. DocScope comprises 1,124 questions derived from 273 documents, with all hierarchical evidence annotations completed by human annotators. We benchmark 6 proprietary models, 12 open-weight models, and several domain-specific systems. Our experiments reveal that answer accuracy cannot substitute for trajectory-level evaluation: even among correct answers, the highest observed rate of complete evidence chains is only 29%. Across all models, region grounding remains the weakest trajectory stage. Furthermore, the primary difficulty stems from aggregating evidence dispersed across long distances and multiple document clusters, while an oracle study identifies faithful perception and fact extraction as the dominant capability bottleneck. Cross-architecture comparisons further suggest that activated parameter count matters more than total scale. The benchmark and code will be publicly released at https://github.com/MiliLab/DocScope.