Auditing Discovery Claims: A Two-Sided Criterion for Agentic Science, with the N

<!-- SC_OFF --><div class="md"><p>Researchers ran 25,000 AI scientist experiments and discovered something that need attention!!</p> <p>AI scientists are producing results without

arXiv:2605.11496v1 Announce Type: new Abstract: Recent published evidence from frontier laboratories shows that contemporary AI models can recognise evaluation contexts, latently

arXiv:2605.08828v1 Announce Type: new Abstract: Large language model agents increasingly operate through environment-facing scaffolds that expose files, web pages, APIs, and logs.

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

arXiv:2604.09251v1 Announce Type: new Abstract: Deep research agents increasingly interleave web browsing with multi-step computation, yet existing benchmarks evaluate these

arXiv:2604.08590v1 Announce Type: cross Abstract: We present AlphaLab, an autonomous research harness that leverages frontier LLM agentic capabilities to automate the full

arXiv:2603.19715v1 Announce Type: new Abstract: Formal verification via interactive theorem proving is increasingly used to ensure the correctness of critical systems, yet

arXiv:2605.15871v1 Announce Type: new Abstract: Toward recursive self-improvement, we investigate LLM agents autonomously designing foundation models beyond standard Transformers.