Multi-Task Evolution for Zero-Shot Cross-Problem Generalization using LLMs

arXiv:2610.03316 · cs.AI · Submitted 2026-10-02 · Read on arXiv

cs.AI

Submitted: 2026-10-02

Updated: 2026-10-08

Code: https://github.com/CIAM-Group/URS

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Generalization — 1× in this paper · explained in 13 episodes

Sources

• SPACE: Unifying Symmetric and Asymmetric Routing Problems for Generalist Neural Solver
• Evolutionary Multi-Task Optimization for LLM-Guided Program Discovery
• Beyond Average Performance: Dynamic Instance Clustering and Specialized Algorithm Design in LLM-Assisted Evolutionary Search
• Enhancing CVRP Solver through LLM-driven Automatic Heuristic Design
• LLM-Driven Instance-Specific Heuristic Generation and Selection

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems