Unverified50% confidenceBenchmarkExact time
On complex tasks such as legal red-line annotation and budget reconciliation, single-step evolution raised accuracy by 35 to 50 percentage points.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/24/2026
First Seen
Valid until: 1/22/2027
Sources
Related Entities
Related Claims
UnverifiedWhen budget and timeline calculations were delegated to an external reliable process rather than inferred by the model itself, accuracy improved by as much as 42 percentage points on weaker models and only 2 to 5 percentage points on stronger models.67% similarUnverified多路径采样意味着数倍推理开销，若需5次独立采样成本会增加至少5倍63% similarUnverifiedRaising the confidence level from 95% to 99% (z-value 2.576) will expand the margin of error by approximately 31% for the same sample size.63% similarUnverifiedThe study data shows that the time spent reviewing each change increased by 49%.61% similarUnverifiedEvolveTrade outperforms fixed-strategy LLM baselines on both Sharpe ratio and cumulative return in most evaluated settings.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1093662API
curl https://kongchang.com/api/v1/knowledge/claims/1093662MCP
get_claim(id=1093662)