Unverified50% confidenceBenchmarkExact time
On CALVIN ABC-D, AtomicRL improves full-task performance over PPO by up to 9.5%.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/22/2026
First Seen
Valid until: 11/5/2026
Sources
Related Entities
Related Claims
UnverifiedOn unseen composite tasks, AdaRSI increased the success rate from 4.6% to 13.8%, roughly a threefold relative improvement.65% similarUnverifiedCompared with single-step models of the same parameter count, Spatial-TRM's context accuracy improves by 44.0% relatively and 9.02 percentage points absolutely.58% similarUnverified英伟达H100相比A100算力提升约3倍，能效比提升约5倍57% similarUnverifiedAmong the 12 model × task combinations, only gpt-5.4-mini showed a statistically significant accuracy improvement on the logical reasoning task: jumping from 15% to 97.5%, with p=0.00056 after Holm correction.57% similarUnverifiedDeepSeek-V3的技术报告显示其MTP机制在多种任务上的平均接受率约为85-90%57% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1083967API
curl https://kongchang.com/api/v1/knowledge/claims/1083967MCP
get_claim(id=1083967)