Compositional Machine Design as Program Synthesis with LLMs
cs.AI, cs.CL, cs.CV, cs.GR, cs.LG
Submitted: 2025-10-16
Updated: 2026-09-01
Comments: 75 pages, 31 figures, Project Page: https://besiegefield.github.io, accepted at EMNLP 2026 Main Conference
Project page: https://besiegefield.github.io
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Constitutional AI: Harmlessness from AI Feedback
- Symbolic Graphics Programming with Large Language Models
- Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models
- Reasoning with Exploration: An Entropy Perspective
- The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models
- On the Multi-turn Instruction Following for Conversational Web Agents
- ShapeLib: Designing a library of programmatic 3D shape abstractions with Large Language Models
- ToolNet: Connecting Large Language Models with Massive Tools via Tool Graph
- How Can Large Language Models Help Humans in Design and Manufacturing?
- Large Language Models: A Survey
- AlphaEvolve: A coding agent for scientific and algorithmic discovery
- Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents
- Self-Reflection in LLM Agents: Effects on Problem-Solving Performance
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Atom of Thoughts for Markov LLM Test-Time Scaling
- Reinforcement Learning for Reasoning in Large Language Models with One Training Example
- LLM-to-Phy3D: Physically Conform Online 3D Object Generation with LLMs
- The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning
- FlowRL: Matching Reward Distributions for LLM Reasoning
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
- 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
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection