Unverified50% confidenceBenchmarkExact time
The SwarmRSI framework comprehensively sets new SOTA across 118 tasks on the three benchmarks OpenProblems, NatureBench and MLEBench Lite.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/20/2026
First Seen
Valid until: 1/18/2027
Sources
SwarmRSI: How a Swarm of Research Agents Achieves Recursive Self-Improvement
bilibili熊二等兵10/18/2026
Related Entities
Related Claims
UnverifiedAt the core of SwarmRSI is a shared graph structure that records all inheritable research states, including each agent's hypotheses, programs, experimental evidence and unresolved requirements.63% similarUnverifiedThe HybridDeepResearch benchmark contains 380 tool-dependent tasks.62% similarUnverifiedThe LSCBench benchmark contains 450 tasks, derived from 150 real vulnerabilities, covering seven languages and 24 CWE categories.60% similarUnverified英伟达软件栈涵盖cuDNN、cuBLAS、NCCL及TensorRT，PyTorch、TensorFlow等主流框架的底层算子均深度依赖这套生态60% similarUnverifiedMC-EvoBench uses a fixed task catalog containing 19 registered evolution chains, of which 12 are primary evaluation chains and 7 are used for calibration and probing59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1073041API
curl https://kongchang.com/api/v1/knowledge/claims/1073041MCP
get_claim(id=1073041)