Unverified50% confidenceFactExact time
The majority-voting strategy causes already-discovered correct workflows to go unselected in 10-19% of tasks in each pool.
1
Sources
50%
Confidence
Long-term
Relevance
11/3/2026
First Seen
Sources
Related Entities
Related Claims
Unverified传统的成功率指标难以全面反映策略的鲁棒性，一个策略可能在90%的常规任务中表现出色却在剩余10%的关键场景中出现灾难性失败64% similarUnverifiedDirectly asking a large model to score candidates often results in scores concentrated in a certain range (e.g., 7–9 points), lacking differentiation.63% similarUnverifiedSelf-Consistency通过多次采样推理路径后投票取多数答案，可进一步提升准确率约5-10个百分点63% similarUnverifiedThe combination of multi-candidate queries plus majority voting plus a judge model appeared to yield an improvement of about +3 points on half the questions, but on the held-out half the gain was exactly 0, while the cost was 5.5 times that of a single call.62% similarUnverifiedThe author's experience: reasoning models typically win on only 12% of tasks and lose on the economics of the remaining 88%.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1129288API
curl https://kongchang.com/api/v1/knowledge/claims/1129288MCP
get_claim(id=1129288)