{"slug": "vlm-fine-tuning-for-end-to-end-combinatorial-optimization", "title": "VLM Fine-Tuning for End-to-End Combinatorial Optimization", "summary": "A new arXiv paper (2609.37175v1) presents a general-purpose vision-language solver that augments textual instance descriptions with input-derived visual representations for end-to-end combinatorial optimization, trained with supervised fine-tuning followed by verifier-guided reinforcement learning. The authors report that the vision-language model generally improves solution quality over its text-only counterpart, with particularly clear gains on more complex combinatorial optimization problems such as CVRP and JSSP, and that the advantage of visual information is more pronounced at large problem scales. The visual inputs contain no gold solutions or solution-derived information.", "body_md": "arXiv:2609.37175v1 Announce Type: new \nAbstract: Large language models (LLMs) have provided a unified interface for end-to-end combinatorial optimization (CO), but textual serialization alone may obscure spatial and relational structures that are important for generating effective CO solutions. This paper presents a general-purpose vision-language solver that augments textual instance descriptions with input-derived visual representations. A single vision-language model (VLM) is applied across different CO tasks and trained using supervised fine-tuning followed by verifier-guided reinforcement learning. While the visual inputs contain no gold solutions or solution-derived information, our experiments show that the VLM generally improves solution quality over its text-only counterpart, with particularly clear gains on more complex CO problems such as CVRP and JSSP. The advantage of visual information is more pronounced at large problem scales.", "url": "https://wpnews.pro/news/vlm-fine-tuning-for-end-to-end-combinatorial-optimization", "canonical_source": "https://www.machinebrief.com/news/vlm-fine-tuning-for-end-to-end-combinatorial-optimization-j0j7", "published_at": "2026-09-30 04:00:00+00:00", "updated_at": "2026-09-30 04:46:59.853205+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "large-language-models", "ai-research", "computer-vision"], "entities": ["arXiv", "CVRP", "JSSP"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/vlm-fine-tuning-for-end-to-end-combinatorial-optimization", "markdown": "https://wpnews.pro/news/vlm-fine-tuning-for-end-to-end-combinatorial-optimization.md", "text": "https://wpnews.pro/news/vlm-fine-tuning-for-end-to-end-combinatorial-optimization.txt", "jsonld": "https://wpnews.pro/news/vlm-fine-tuning-for-end-to-end-combinatorial-optimization.jsonld"}}