Implement Agentic logoImplement Agentica Clouda Company

    Reviewed current signal · 2026-08-27

    AgentFold uses multi-agent search to modify a protein-folding codebase

    Reviewed through September 18, 2026

    2026-08-27 · Reviewed current signal

    AgentFold uses multi-agent search to modify a protein-folding codebase

    Era
    Current reviewed signal
    Theme
    AI for science
    Evidence form
    Preprint
    Source of record
    arXiv / AgentFold authors
    Source tier
    A
    Impact
    High
    School / paradigm
    Not recorded — current signals carry no formal school
    Application
    Protein modeling and scientific code discovery
    Researchers
    Not recorded

    Understand

    Plain-language record, transferred from the reviewed source module.

    What changed. Agents proposed, implemented, debugged, evaluated, and analyzed about 80 ESMFold variants using roughly 5,000 GPU-hours and 170M LLM tokens; the best reported variant improved lDDT 7.5% over independent Codex proposals.

    Technique / discovery. Multi-agent closed-loop code search with MCTS-style resource allocation.

    Apply

    Professional implication, only where the reviewed record states one.

    Why it matters. Executable search with retained failures can explore research interventions beyond one-shot suggestions.

    Application. Protein modeling and scientific code discovery

    Verify

    Evidence status, stated limitations, and the external sources this record actually carries.

    Evidence maturity. Preprint (source tier A)

    Identified bottleneck. One codebase, high compute, best-of-run reporting, and no matched expert-team baseline.

    Caveat / evidence note. Fresh author-reported arXiv preprint without independent replication.

    Review status. Reviewed. User requested: Yes.

    Reproduce

    A reproduction tutorial is linked only when one exists for this exact record.

    AgentFold closed-loop search — published with the 2026-08-28 briefing edition.

    Cite or share

    Related