RUMP SCIENCE

Google spinoff Isomorphic Labs in race to shake up cancer drug development

gnews-models · OCT 31

[PAPER] STUDY: Machine learning finds hidden second phase transition in polymer stretching under elongational flow

arxiv-science · OCT 29

[PAPER] STUDY: AI submissions to research-level math challenge include correct solutions unlike the official ones...

arxiv-science · OCT 29

[PAPER] STUDY: Best AI scores 63.5% on research decisions vs 73.4% for fresh researchers

arxiv-science · OCT 15

[PAPER] STUDY: AI agents pick research questions, derive theory and test it on quantum spins in diamond

arxiv-science · OCT 29

[PAPER] Paper: LLM agent designs algorithms and proves their runtime bounds... no empirical comparison in the pipeline

arxiv-science · OCT 26

[PAPER] New ClaimNov tool catches 97% of disguised papers at 1.5% false-alarm rate

arxiv-science · OCT 27

[PAPER] Expert review picks out 37 CAR-T hypotheses as both novel and biologically plausible...

arxiv-science · OCT 28

[PAPER] STUDY: AI agents diagnosed their own cross-reactivity, restored specificity from 19.1% to 72.4%

arxiv-science · OCT 17

Parse and Nomic launch Cascade, an AI tool for immune drug discovery

gnews-discovery · NOV 1

[PAPER] Development version of 'Agentic Scientist' system submits a paper, accepted at ALIFE 2026

arxiv-science · OCT 13

[PAPER] Self-building labs: AI that designs, builds and runs its own laboratory from an empty room

arxiv-science · OCT 16

[PAPER] System proposes ranked candidate years for 56 undated entries of ADART IV

arxiv-science · OCT 25

[PAPER] STUDY: AI predicts electron density so well one quantum step replaces the full iteration

arxiv-science · OCT 29

[PAPER] STUDY: Hidden dislocation hierarchies change how grain boundaries slide... GBClaw agentic AI framework used

arxiv-science · OCT 20

[PAPER] STUDY: AI agents' forecasts of experiment outcomes no more accurate than a fresh copy of the same model

arxiv-science · OCT 29

[PAPER] STUDY: Claude Opus tops published science models by 10.4%, but agents fall short of real insight...

arxiv-science · OCT 20

[PAPER] STUDY: Tabular foundation models can outperform bespoke estimators using only in-context learning

arxiv-science · OCT 29

[PAPER] AI AGENT PICKS ITS OWN RESEARCH QUESTIONS, WRITES FIVE PAPERS ON A LAPTOP... NO RESEARCH INPUT FROM HUMANS

arxiv-science · OCT 29

[PAPER] AI research team beats GDN2 at 1.3B scale after autonomously searching for new linear attention designs

arxiv-science · OCT 20

[PAPER] STUDY: Failures in AI-written papers are mostly misattributed numbers, not overt cheating

arxiv-science · OCT 28

[PAPER] PULSES: Multi-agent AI system automates excited-state molecule modeling within expert-set limits

arxiv-science · OCT 23

[PAPER] STUDY: MatOS agent beats Codex CLI and Claude Code on science benchmarks with the same base model

arxiv-science · OCT 25

[PAPER] STUDY: AI model finds how defects form in diamond, uncovering pathways missing from its training data

arxiv-science · OCT 19

[PAPER] STUDY: ReactNexus AI maps chemical reaction networks from reactant graphs alone, no templates needed

arxiv-science · OCT 28

[PAPER] STUDY: Automated detector flags research-integrity violations in 99.7% of 300 AI research-agent trajectories

arxiv-science · OCT 22

[PAPER] STUDY: AI SCIENTISTS MAKE PARTIAL PROGRESS, RARELY FINISH... RUBRIC SCORES TOP OUT AT 59%

arxiv-science · OCT 29

[PAPER] STUDY: Autonomous research agents tested on 15 medical tasks... competitive scores, shaky risk estimates

arxiv-science · OCT 18