Search papers, labs, and topics across Lattice.
3
0
5
2
Predictive world models, not just static feedback, unlock substantial gains in recursive self-improvement across diverse domains, from code to scientific discovery.
This work introduces and releases ScienceBuddy, an interactive scientific research workspace that brings continually improving scientific agents into researchers'everyday workflows and presents case studies of researcher interaction, harness refinement, and model learning, with the benchmark cases spanning four scientific task families.
Agents can exhibit significant performance gains from retained experience, but the pathways to these improvements are often unclear and model-dependent.
