Evolving in Thought Space: Training a Small Model at Test Time Unlocks Better Discoveries Paper • 2610.06269 • Published 7 days ago
ScholarCatalyst: A Benchmark for Retrieving Papers That Inspire New Research Paper • 2610.02202 • Published 11 days ago • 14
SPADE: Self-Play in Adaptive Synthetic Executable Environments Paper • 2608.19197 • Published Aug 19 • 56
Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents Paper • 2602.13379 • Published Feb 13 • 4
SPADE: Self-Play in Adaptive Synthetic Executable Environments Paper • 2608.19197 • Published Aug 19 • 56
msr-spare-1/qwen3-4b-0630-tooluse-eval-aligned-r32-spare-games-envs Viewer • Updated Aug 13 • 1 • 272
msr-spare-1/qwen3-30b-0718-gpt55-static-balanced-7872-spare-games-envs Viewer • Updated Aug 13 • 1 • 260
msr-spare-1/qwen3-30b-0622-fixed-corpus-gpt53-actor-spare-games-envs Viewer • Updated Aug 13 • 1 • 170
msr-spare-1/qwen3-30b-0617-plateau-6skill-noprop-nomem-spare-games-envs Viewer • Updated Aug 13 • 1 • 611