arXiv:2610.20457v1 Announce Type: new Abstract: Co-scientists and agentic scientific claim verifiers are increasingly used to assess claims across the sciences. Natural-language scientific claims, wr...
The paper examines how AI‑written research papers often contain misattributed numerical claims. By re‑analyzing 540 judgments from a benchmark of nine AI agents on fifteen research problems, the authors manually labeled 256 claims and found that most failures stem from misalignment between the paper and the underlying work rather than outright cheating. They propose a deterministic claim‑to‑evidence checker that achieves over 90% precision and, when combined with an LLM verifier, offers a more reliable audit of AI‑generated research.
VeriHarness is a method that enhances verification for large language model agents tackling long‑horizon tasks without needing reference answers at test time. It transforms the base LLM into an agentic verifier by providing a workspace, evidence tools, and reusable verification skills, using disagreement resolution and consensus challenge to evaluate competing claims. Across five benchmarks and two frontier models, VeriHarness outperforms baselines, achieving significant performance gains and demonstrating self‑improvement of verification skills from failure feedback.
As autonomous AI agents take on every stage of scientific inquiry, research output is expanding far beyond human review capacity. Yet scientific communication still relies on natural-language prose: a...
arXiv:2606. 11851v1 Announce Type: new Abstract: Open-ended scientific discovery asks agents to move beyond executing analyses for predefined questions.
arXiv:2609.33357v2 Announce Type: replace Abstract: Reliable automated research requires agents to vet data, verify analyses, and generate hypotheses grounded in trustworthy evidence, potentially red...
arXiv:2605.22875v2 Announce Type: replace Abstract: Long-horizon mathematical reasoning fails less often because a model cannot produce a valid next step than because an agent fails to maintain and e...
TruthInsightBench is a new benchmark designed to evaluate automated scientific discovery agents by presenting them with 40 blind tasks drawn from peer‑reviewed studies across ten domains. Each task provides only a neutral objective and frozen data, withholding source conclusions, expected values, and analysis paths, forcing agents to determine which claim the data support. A fixed LLM‑based judge scores agents on evidentiary maturity across six dimensions, using 29 artifact‑grounded items, enabling fully automated, repeatable evaluation without human grading.
arXiv:2610.14381v1 Announce Type: new Abstract: Large language models are increasingly used as scientific assistants, yet we still lack reliable ways to evaluate whether they can investigate a system...
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.
arXiv:2609.27297v2 Announce Type: replace Abstract: Agentic science envisions many autonomous agents investigating concurrently while building on a shared, evolving body of scientific knowledge. This...
arXiv:2607. 05682v1 Announce Type: new Abstract: LLM systems for scientific discovery increasingly assist with ideation, literature synthesis, experiment planning, and report generation, but the first research question they propose can remain difficult to audit: it may sound plausible without exposing the mechanism, falsifier, or assumption that a scientist should inspect.