Specification-Guided Synthesis of Deadlock-Free Communication Protocol Refinements with Large Language Models
cs.SE, cs.AI
Submitted: 2026-07-30
Updated: 2026-10-13
Terminology
Sources
- Program Synthesis with Large Language Models
- Evaluating Large Language Models Trained on Code
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
- Qwen2.5-Coder Technical Report
- A Scalable Communication Protocol for Networks of Large Language Models
- Constrained Decoding for Fill-in-the-Middle Code Language Models via Efficient Left and Right Quotienting of Context-Sensitive Grammars
- Flexible and Efficient Grammar-Constrained Decoding
- LDP: An Identity-Aware Protocol for Multi-Agent LLM Systems
- Qwen2.5 Technical Report
- Code Llama: Open Foundation Models for Code
- ConformalNL2LTL: Translating Natural Language Instructions into Temporal Logic Formulas with Conformal Correctness Guarantees
- Generative Emergent Communication: Large Language Model is a Collective World Model
- Preguss: It Analyzes, It Specifies, It Verifies
- Efficient Guided Generation for Large Language Models
Related papers
- Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
- GitSkills: A Dataset of Agent Skills on GitHub
- SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces
- PackMonitor: Enabling Zero Package Hallucinations Through Decoding-Time Monitoring
- IntentCoding: Amplifying User Intent in Code Generation
- Incentives and Outcomes in Bug Bounties