{"slug": "llm-as-an-improver-turning-verification-into-better-candidates", "title": "LLM-as-an-Improver: Turning Verification into Better Candidates", "summary": "A new arXiv paper (2609.19515v1) introduces LLM-as-an-Improver and the Verify--Repair--Reselect (VRR) method, which uses verification feedback to generate and reselect improved candidates rather than only ranking a fixed candidate pool. VRR retains the initial winner while conditionally generating three complementary alternatives: repaired versions of the winner and runner-up, and a solution based on a new approach, filtering invalid and duplicate candidates using only inference-time information. Across diverse models and code-generation and reasoning benchmarks, VRR improves over fixed-pool verifier-based selection in many settings and can recover correct solutions even when all candidates in the initial pool are incorrect.", "body_md": "arXiv:2609.19515v1 Announce Type: new \nAbstract: Verifier-based selection improves LLM performance by generating multiple candidate solutions and using a verifier to select the most promising one. However, existing methods typically treat verification only as a ranking step and discard its feedback once a fixed candidate pool has been evaluated. In this paper, we ask whether verification can also improve the candidate set itself. To this end, we introduce LLM-as-an-Improver and propose Verify--Repair--Reselect (VRR), which uses verification feedback to generate and reselect improved candidates. VRR retains the initial winner while conditionally generating three complementary alternatives: repaired versions of the winner and runner-up, and a solution based on a new approach. It filters invalid and duplicate candidates using only inference-time information and then reselects the final answer under the original evaluation criteria. Across diverse models and code-generation and reasoning benchmarks, VRR improves over fixed-pool verifier-based selection in many settings and can recover correct solutions even when all candidates in the initial pool are incorrect. These results highlight a broader role for LLMs as improvers: verification feedback can not only select among existing solutions but also construct stronger candidates beyond the initial pool.", "url": "https://wpnews.pro/news/llm-as-an-improver-turning-verification-into-better-candidates", "canonical_source": "https://arxiv.org/abs/2609.19515", "published_at": "2026-09-18 04:00:00+00:00", "updated_at": "2026-09-18 04:25:35.665227+00:00", "lang": "en", "topics": ["large-language-models", "ai-research", "machine-learning", "artificial-intelligence"], "entities": ["arXiv", "LLM-as-an-Improver", "Verify--Repair--Reselect"], "alternates": {"html": "https://wpnews.pro/news/llm-as-an-improver-turning-verification-into-better-candidates", "markdown": "https://wpnews.pro/news/llm-as-an-improver-turning-verification-into-better-candidates.md", "text": "https://wpnews.pro/news/llm-as-an-improver-turning-verification-into-better-candidates.txt", "jsonld": "https://wpnews.pro/news/llm-as-an-improver-turning-verification-into-better-candidates.jsonld"}}