Unverified50% confidenceFactExact time
@k pressure can be fully realized through single-completion training, matching the performance of multi-completion @k optimizers at only a fraction of their cost.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/3/2026
First Seen
Valid until: 2/1/2027
Sources
Related Entities
Related Claims
UnverifiedSingle-completion training means that at each policy update, only one completion is sampled per prompt, yet the learning pressure of the @k objective is simulated through reward transformation or regularization design.77% similarUnverifiedThis study derives closed-form optimal policies for the pass@k and max@k objectives under KL regularization, showing that @k optimization is essentially redistributing learning pressure according to problem difficulty, shifting the optimization focus from easy problems to hard ones.75% similarUnverifiedLISCO adopts a self-supervised training approach, using the degree to which KKT conditions are satisfied as the objective, without requiring pre-computed optimizer solutions as labels.66% similarUnverifiedKimi K2.6能根据问题复杂度自适应调整输出长度,这一能力通过Post Training阶段的长度校准技术实现61% similarUnverified最大似然估计训练目标等价于最小化模型分布与训练数据经验分布之间的KL散度61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1130874API
curl https://kongchang.com/api/v1/knowledge/claims/1130874MCP
get_claim(id=1130874)