Sketch-and-Verify improves small-LLM code generation on HumanEval+ by factorizing search into K algorithmic sketches and M fillings each, outperforming flat sampling by up to 32 percentage points at matched budget while remaining cheaper than upgrading model tier.
Advances in Neural Information Processing Systems , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
Execution-based selectors for LLM code candidates outperform textual voting by large margins across configurations, with input generation quality mattering more than the specific aggregation rule.
StraTA improves LLM agent success rates to 93.1% on ALFWorld and 84.2% on WebShop by sampling a compact initial strategy and training it jointly with action execution via hierarchical GRPO-style rollouts.
citing papers explorer
-
Sketch-and-Verify: Structured Inference-Time Scaling via Program Sketching
Sketch-and-Verify improves small-LLM code generation on HumanEval+ by factorizing search into K algorithmic sketches and M fillings each, outperforming flat sampling by up to 32 percentage points at matched budget while remaining cheaper than upgrading model tier.
-
Semantic Voting: Execution-Grounded Consensus for LLM Code Generation
Execution-based selectors for LLM code candidates outperform textual voting by large margins across configurations, with input generation quality mattering more than the specific aggregation rule.
-
StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction
StraTA improves LLM agent success rates to 93.1% on ALFWorld and 84.2% on WebShop by sampling a compact initial strategy and training it jointly with action execution via hierarchical GRPO-style rollouts.