{"ID":5675447,"CreatedAt":"2026-07-03T01:40:09.565152011Z","UpdatedAt":"2026-07-08T13:27:10.811688413Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.02329","arxiv_id":"2607.02329","title":"Grounded autonomous research: a fault-tolerant LLM pipeline from corpus to manuscript in frontier computational physics","abstract":"Autonomous-research agents have demonstrated end-to-end LLM automation in machine-learning sandboxes where execution provides calibration. Frontier physical science differs categorically: physical reasoning underlies every methodology choice, toolchains are often underdocumented, and calibration must come from external literature anchors - which unscaffolded agents cite but do not confront, hallucinating plausible, unverifiable results from internal priors. We present a pipeline that runs end-to-end from a corpus of 11,083 recent condensed-matter physics arXiv papers to a publication-grade manuscript with three substantive physics findings (here on altermagnetic piezomagnetism): the agent autonomously conceives a research direction by mapping the corpus, calibrates methodology by reproducing published references, conducts novel first-principles computations, and writes the manuscript - grounded in literature throughout, across 47 fresh-context sessions in six phases sharing only on-disk state, with 2,162 literature-consultation events. Fault tolerance emerges from redundancy: fresh-context isolation, distributed grounding, and adversarial review catch what any single session misses; pre- and post-pilot stages are fully autonomous, and pilot requires bounded human intervention only at reproduction failures - operational knowledge curation, not scientific direction. Two paired failure modes - a pre-architecture baseline and a no-pilot ablation - isolate structurally enforced numerical confrontation at calibration checkpoints as the operative grounding mechanism. The primitives, characterized failure modes, and quantified intervention pattern lay a foundation for autonomous research in high-stakes scientific domains beyond computational physics.","short_abstract":"Autonomous-research agents have demonstrated end-to-end LLM automation in machine-learning sandboxes where execution provides calibration. Frontier physical science differs categorically: physical reasoning underlies every methodology choice, toolchains are often underdocumented, and calibration must come from external...","url_abs":"https://arxiv.org/abs/2607.02329","url_pdf":"https://arxiv.org/pdf/2607.02329v1","authors":"[\"Haonan Huang\"]","published":"2026-07-02T15:35:41Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cond-mat.mtrl-sci\",\"physics.comp-ph\"]","methods":"[\"Large Language Model\"]","has_code":false}