arXiv:2610.06650v2 Announce Type: replace Abstract: Wikidata is one of the largest open knowledge bases, yet answering a complex question over it still requires a SPARQL query that names the right en...
The paper introduces Iris-mini and Iris-pro, two search agents trained at 35B and 397B parameter scales. They use a novel data pipeline that constructs reverse‑engineered multi‑hop queries from web hyperlinks, filters trajectories, and alternates supervised fine‑tuning with reinforcement learning in a process called SFT‑RL climbing. Evaluations on several benchmarks show that, with inference‑time context management, the agents achieve the best open‑source results in their parameter ranges.
arXiv:2509. 00761v4 Announce Type: replace Abstract: Large language models are increasingly deployed for legal question answering, where evaluations typically focus on multiple-choice accuracy.
The paper presents a deployed system for answering questions over normative documents that is aware of document version and scope. It evaluates a hosted retrieval service against a governed system that applies explicit rules for version and scope resolution, finding the governed system achieves a higher score (97.7 vs 88.1). The study includes a public benchmark, evaluation scripts, and reports commercial deployment metrics, such as 1,126 users and 100,000 calls per day by April 2026.
arXiv:2607. 26070v1 Announce Type: cross Abstract: Large language model (LLM)-based agentic search systems are often evaluated as if the underlying LLM were the only component that matters, yet their measured performance also depends on the surrounding search environment: the Wikipedia snapshot, preprocessing pipeline, chunking policy, retrieval backend, tool schema, observation format, and answer submission rule.
arXiv:2609.16519v1 Announce Type: new Abstract: Scientific research increasingly relies on large, heterogeneous data sources, motivating interest in retrieval-augmented generation (RAG) systems that...
arXiv:2608. 20106v1 Announce Type: new Abstract: We introduce OenoBench, a wine-domain knowledge benchmark of 3,266 multiple-choice questions across six pillars (regions, grape varieties, viticulture, winemaking, producers, business) and four difficulty tiers.
arXiv:2607. 28618v1 Announce Type: cross Abstract: Chemistry literature synthesis often requires assembling specific findings scattered across many publications, yet existing literature-search systems primarily return ranked document lists.
Optimist Deep Research is an open‑source agent that conducts literature research as an iterative, state‑centric process. It breaks a research question into a tree of subquestions, uses search intents to query multiple scholarly databases, and merges results into a provenance‑preserving document registry. The agent iteratively expands the registry via citation snowballing, evaluates evidence, and refines the research plan through a critic that can add, split, rephrase, deprioritize, or close subquestions, ultimately producing a report with every citation linked to a retrieved document.
arXiv:2607. 28229v1 Announce Type: cross Abstract: The web is increasingly accessed by AI agents rather than humans.
CiteVQA is a benchmark that evaluates multimodal large language models on both answering document questions and providing element‑level bounding‑box citations for the evidence used. It contains 1,897 questions across 711 PDFs in seven domains and two languages, with ground‑truth citations generated via an automated pipeline and strict quality control. The evaluation metric, Strict Attributed Accuracy (SAA), rewards a prediction only when both the answer and the cited region are correct, revealing widespread attribution hallucination in current models.
Correctly answering a question grounded in normative documents often depends on information outside any single passage: whether the retrieved document is the version currently in force; whether it app...