arXiv:2607. 20527v1 Announce Type: new Abstract: Agentic LLM systems such as OpenScholar and PaperQA2 read the scientific literature and return cited answers, and both they and their benchmarks already check whether those citations hold, with a fixed attribution model or human graders.
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.
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 introduces a claim‑anchored execution contract that binds a tool‑using agent’s emitted claim to its exact source span, the ordered execution prefix that produced it, and the source version and access state observed. Each receipt contains deterministic anchors, source identifiers, offsets, hashes, quotes, and a domain‑separated execution commitment, allowing a verifier to reconstruct these bindings before semantic or task labels are joined. The contract defines seven independently testable properties and demonstrates high detection rates against cross‑object attacks, with strong performance on conflict‑aware support guard evaluations.
ClaimScope is a 72‑task benchmark that audits mathematical claims by requiring a verdict, scope, counterexample, and repair, covering areas such as optimizer‑state transport and exact $2 imes2$ linear algebra. The study evaluates Qwen3‑8B using a witness checker that only examines the model’s submitted state, showing that verifier feedback improves counterexample acceptance and safe completions compared to generic feedback. The results demonstrate that separating claim classification from executable evidence can yield gains in witness‑structure correction without necessarily improving broader reasoning.
The paper introduces a claim‑gated audit framework for generative search, ensuring that a query, source, and answer tuple is only considered resolved when relationship evidence, answer adoption, materiality, and disclosure are all present. It distinguishes this audit endpoint from citation support and review priority, tying decisions to versioned evidence spans and implementing a reference checker to enforce the contract. Experiments on a synthetic dataset confirm that the system correctly handles all 81 predicate combinations and rejects 192 malformed records, while ablation studies isolate endpoint logic from missing‑evidence handling.
arXiv:2607. 01223v1 Announce Type: new Abstract: When should an AI system's answer be trusted?
arXiv:2607. 25364v1 Announce Type: new Abstract: Tool-using agents expose structured calls but commonly attach free-form rationales.
arXiv:2607. 12650v1 Announce Type: cross Abstract: Tool access alone does not make LLM empirical reasoning governable: accepted outputs need not descend from attested evidence, and accepted deductions need not hold up under formal scrutiny.
AtomCite is an agentic framework that verifies and corrects page‑level citations in multi‑page documents by parsing answers into claims, checking each claim against the cited page image, and applying a deterministic repair policy. The authors introduce DocCite, the first benchmark for this task, built on MP‑DocVQA and DUDE, containing 928 injected instances and 1,909 verified natural errors. Across Gemini, Claude, and GPT models, AtomCite achieves about 93% verification accuracy and improves citation precision from 34% to 87‑90%, while also enhancing hallucination detection in open‑source models.
The paper introduces ClaimReceipt, a specification and verifier that checks whether a claim in an agent evaluation can be recomputed from retained evidence (sufficiency) and whether the evidence covers the entire experiment set (coverage). Using the CR‑2 verifier on 1,392 historical records, the authors demonstrate accurate reproduction of audit verdicts, non‑redundant field groups, and zero false positives on semantic faults. In a prospective CR‑3 run, the system correctly flags missing receipts and preserves coverage when private evidence is withheld, while adding minimal overhead to inference time and transaction size.
Legal Research Bench (LRB) is a new benchmark comprising 413 open-ended U.S. legal research questions, each paired with a gold answer, supporting authorities, and a binary grading rubric. The study evaluates thirteen advanced language‑model agents using web search, case‑law search, page parsing, and retrieval tools, scoring responses only when all required criteria are met and cited authorities verify. Results show that even the best model, Claude Opus 4.8, achieves full correctness on only 42.9% of questions, with performance varying by legal area and task complexity, and no clear link between more tool calls or inference cost and higher accuracy.