Symbolic Synthesis with Token-Level LLM Guidance
cs.PL
Submitted: 2026-11-08
Updated: 2026-11-08
Code: https://github.com/cvc5/cvc5
Terminology
Sources
- Pluto: A Benchmark for Evaluating Efficiency of LLM-generated Hardware Code
- Guiding LLMs The Right Way: Fast, Non-Invasive Constrained Generation
- VerMCTS: Synthesizing Multi-Step Programs using a Verifier, a Large Language Model, and Tree Search
- Language Models are Few-Shot Learners
- A benchmark for vericoding: formally verified program synthesis
- A New Era in Software Security: Towards Self-Healing Software via Large Language Models and Formal Verification
- Evaluating Large Language Models Trained on Code
- Recursive Program Synthesis from Sketches and Mixed-Quantifier Properties
- Can LLMs Perform Synthesis?
- Tree Automata and Tree Grammars
- Djinnlang: Higher-Level Programming by Unambiguous Specification with an LLM in the Compiler
- RealBench: Benchmarking Verilog Generation Models with Real-World IP Designs
- Finding Inductive Loop Invariants using Large Language Models
- Evaluating Language Models for Efficient Code Generation
- Competitive Programming with Large Reasoning Models
- CLEVER: A Curated Benchmark for Formally Verified Code Generation
- VERINA: Benchmarking Verifiable Code Generation
- BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions
Related papers
- The Best of Times, the Worst of Times: Moment-Based Analysis of Probabilistic Cost Structures
- Formal Verification of an Out-of-Order Multiprocessor against an In-Order Weak-Memory ISA
- Fuss-free cumulative universes: theory and practice
- High-Level Synthesis of Efficient Pipelines with Visibility Control
- Model Checking Probabilistic Multiparty Session Types
- A Type System for Communication-Safe Hardware Design