Interpreting Neural Combinatorial Optimization via Evolving Programmatic Bottlenecks
cs.AI, cs.LG
Submitted: 2026-06-18
Updated: 2026-11-07
Terminology
Sources
- Learning to Intervene on Concept Bottlenecks
- TextGrad: Automatic "Differentiation" via Text
- Neural Combinatorial Optimization with Reinforcement Learning
- Post-hoc Concept Bottleneck Models
- Probing Neural Combinatorial Optimization Models
- Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Model
- Evaluating Large Language Models Trained on Code
- Program Synthesis with Large Language Models
- Opening the AI black box: program synthesis via mechanistic interpretability
- Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- 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
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents