Unverified50% confidenceSolutionExact time
Solving the combinatorial optimization problem typically uses greedy or approximate algorithms: at each step, select the partial solution that most improves the estimated pool pass@k, until the budget is reached.
1
Sources
50%
Confidence
Long-term
Relevance
10/23/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe method treats pruning as a combinatorial optimization problem: selecting a subset from all partial solutions to maximize the probability that the subset, after continued generation, contains at least one correct solution.72% similarUnverifiedThe trade-off of first-order methods is that convergence typically requires more iterations and is more sensitive to the numerical conditioning of the problem.71% similarUnverifiedMetaheuristic optimization algorithms generally suffer from high computational overhead, and their search processes are stochastic, meaning convergence results may vary across runs.71% similarUnverifiedOccupancy-measure-based algorithms rewrite the policy optimization problem as convex optimization over the occupancy measure polytope, thereby globally controlling error accumulation across all state-action pairs, which is the fundamental reason their regret bound has one fewer H factor.70% similarUnverifiedMechanism two: in the intermediate regime, pooling the generation counts of different questions is more effective than estimating each answer distribution separately, and only logarithmic gains can be obtained from additional questions.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1088233API
curl https://kongchang.com/api/v1/knowledge/claims/1088233MCP
get_claim(id=1088233)