Anthropic news: research

4 research items

Journal articles, academic blogs, think-tank reports and papers in this section, newest first. Back to the news.

arXiv (research papers) Jizhou Guo Tech policy

Same Papers, Different Verdicts: Tracing Version Drift in LLM Peer Review

Venues and benchmarks read LLM review scores as measurements of a paper, while providers replace their models within months. We audit twenty frontier models from OpenAI, Google and Anthropic on ICLR 2027 submissions while they were under review, with tests registered before the decisions. Between an earlier and a later version of Claude Opus and of Gemini, the share of papers placed on the accept side falls by 52 and 53 percentage points on 183 and 60 randomly drawn…

Read at arXiv (research papers)

arXiv (research papers) Rayed AlGhamdi Tech policy

Reliability of Claude Code as an Agentic AI Grading System for Handwritten University Exams

This study examines the reliability of Claude Code, an agentic deployment of the Claude Opus 4.6 large language model, as a grading system for handwritten university exams. Four research questions addressed agreement with expert human grading on total scores (RQ1), agreement across five question types from multiple choice to evaluative judgement (RQ2), consistency across two independent grading sessions one week apart (RQ3), and the accuracy of AI-generated feedback (RQ4)…

Read at arXiv (research papers)

Frontiers in Sustainable Food Systems Başak Öney

Human and planetary health implications of AI-generated diet plans: a comparative assessment using the EAT-Lancet framework

IntroductionArtificial intelligence (AI) is increasingly being used to support dietary planning, with growing interest in generating recommendations that are both nutritionally adequate and environmentally sustainable. This study compared meal plans generated by three AI platforms, OpenAI ChatGPT (GPT 5.5 Instant), Google Gemini (Gemini 3 Flash), and Anthropic Claude (Claude Opus 4.8), across different clinical scenarios using the energy adjusted EAT–Lancet Diet Index 2.0…

Read at Frontiers in Sustainable Food Systems

arXiv (research papers) Hui Zhao Heurion Research SI

Aegis OS: A Transactional Multi-Tenant Operating System Runtime for Eliminating Authorization Fatigue in Autonomous Coding Agents

Autonomous coding agents such as Google Antigravity (agy), Anthropic Claude Code (claude), and OpenAI Codex CLI (codex) execute multi-step software engineering workflows on workstations and cloud hosts. Existing agent environments face a Security-Autonomy Dilemma: operators must choose between per-action confirmation prompts, which interrupt workflows on 45%-57% of tool calls and induce authorization fatigue, or unconfined execution (--yolo / --dangerously-skip-permissions)…

Read at arXiv (research papers)