acceptodds
Desk rejected at ICLR 2027

Automating Combinatorial Optimization Knowledge Transfer with LLMs

Desk rejected at ICLR 2027, so left out of the paper lists and the map.

Abstract

Developing combinatorial optimization algorithms is time-consuming and labor-intensive. While recent LLM-based methods enable automated algorithm design, they often overlook the transferable knowledge encoded in mature solvers. In this paper, we study Automated Knowledge Transfer (AutoKT), which asks: to what extent can LLMs automate knowledge transfer from a source solver to a target problem? To this end, we formalize the algorithmic knowledge space and transfer process, defining a comprehensive evaluation protocol across three tiers: same-domain, cross-domain, and new-domain transfer. We then develop a three-stage agentic framework: a local migration stage that incrementally constructs a scaffold from localized source knowledge, a global migration stage that coordinates the transferred knowledge, and a validation stage to ensure correctness. Extensive experiments demonstrate AutoKT's effectiveness across all three tiers, outperforming both strong domain heuristics and general-purpose coding agents. We further provide in-depth analyses revealing key insights into AutoKT's behavioral patterns and knowledge transferability, offering useful takeaways for the community.

Primary area:
optimization
Keywords:
knowledge transfer

Related papers

Discussion (0)

Sign in to comment.