LLM agents run and revise a quantum-spin experiment in diamond
After drift made a first run inconclusive, agents changed the protocol and the revised experiment supported theory.
Stories per day · 30 days
1 RSS
Relatedbenchmarks2agent-swarm1autonomous-lab1autoresearch1boltz1diamond1dna-encoded-libraries1drug-discovery1hermes1leash-bio1llm-evaluation1minos1mle-bench1multi-agent1open-dataset1quantum-spins1recursive-self-improvement1scientific-judgment1
9 stories, newest first · one card per story
Stories tagged #scientific-agents
Lab-in-the-Loop at Compute Speed — Ian Quigley, Leash Bio
Leash Bio’s Ian Quigley discusses DNA-encoded library data and the new Minos dataset for scientific agents.
SciΠvot: frontier models lag humans on research judgment
Best project-condition accuracy is 63.5%, versus 73.4% for fresh researchers on the same cases.
SwarmRSI: Recursive Self-Improvement through Evolving Scientific Agent Swarm
SwarmRSI reports state-of-the-art recursive self-improvement for scientific agent swarms on three research benchmarks.
AutoSciBench: Autonomous Benchmark Generation for Evaluating Scientific Agents
AutoSciBench automatically generates scientific-agent benchmarks that lower solver accuracy versus human-curated tests.
ScholarCatalyst: A Benchmark for Retrieving Papers That Inspire New Research
ScholarCatalyst asks models to retrieve papers that inspired 207 CS projects; agents fail to beat embedding retrieval.
ScholarCatalyst: A Benchmark for Retrieving Papers That Inspire New Research
ScholarCatalyst finds agents no better than embeddings at retrieving papers that inspire new research.
ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents
ScienceBuddy couples harness evolution with model reinforcement learning so scientific agents continually self-improve from researcher feedback in an interactive workspace.
ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents
ScienceBuddy released: interactive scientific agent workspace coupling harness evolution with model reinforcement learning for continual self-improvement across four scientific task families.