SciGame tests agents on real and counterfactual scientific laws
On five frontier models, recovering the exact symbolic form stays the main bottleneck.
Stories per day · 30 days
2 RSS
Relatedbenchmarks1llm-agents1lora1physical-reasoning1policy-improvement1qwen1robotics1scientific-discovery1scigame1self-evolution1simulation1vlm1world-models1
5 stories, newest first · one card per story
Stories tagged #counterfactuals
Rollback backtracks world models to improve robot policies
Absolute success gains were 10.67%, 11.11%, and 11.85% on three real-world tasks versus the strongest baseline.
PhysEvolve trains VLMs on executable worlds for physical reasoning
From Qwen3-VL-8B-Instruct, the paper reports PhysBench Throwing up 8.8 and ContPhy Goal-Pit up 24.4 points.
Attenuated in-context identification in time-series foundation models: diagnosis under counterfactual inputs and repair by synthetic forced-system fine-tuning
Time-series foundation models attenuate counterfactual dynamics; synthetic forced-system fine-tuning partly restores response magnitude.
SocioVerse2: A Longitudinal Dynamic Social Simulation Framework under a Human-AI Co-evolutionary Paradigm
SocioVerse2 adds longitudinal interventions and researcher-controlled loops to generative-agent social simulation.