Pith. sign in

REVIEW 6 cited by

Rango: Adaptive Retrieval-Augmented Proving for Automated Software Verification

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2412.14063 v3 pith:37GEVRQX submitted 2024-12-18 cs.SE cs.AI

Rango: Adaptive Retrieval-Augmented Proving for Automated Software Verification

classification cs.SE cs.AI
keywords rangoproofproofssynthesistheoremspremisesrelevantverification
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Formal verification using proof assistants, such as Coq, enables the creation of high-quality software. However, the verification process requires significant expertise and manual effort to write proofs. Recent work has explored automating proof synthesis using machine learning and large language models (LLMs). This work has shown that identifying relevant premises, such as lemmas and definitions, can aid synthesis. We present Rango, a fully automated proof synthesis tool for Coq that automatically identifies relevant premises and also similar proofs from the current project and uses them during synthesis. Rango uses retrieval augmentation at every step of the proof to automatically determine which proofs and premises to include in the context of its fine-tuned LLM. In this way, Rango adapts to the project and to the evolving state of the proof. We create a new dataset, CoqStoq, of 2,226 open-source Coq projects and 196,929 theorems from GitHub, which includes both training data and a curated evaluation benchmark of well-maintained projects. On this benchmark, Rango synthesizes proofs for 32.0% of the theorems, which is 29% more theorems than the prior state-of-the-art tool Tactician. Our evaluation also shows that Rango adding relevant proofs to its context leads to a 47% increase in the number of theorems proven.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. FVSpec: Real-World Property-Based Tests as Lean Challenges

    cs.SE 2026-05 conditional novelty 7.0

    A new benchmark of 9,415 Lean 4 specifications derived from 2,772 scraped Python property-based tests, plus a three-agent LLM transpilation pipeline and proof-generation baselines.

  2. Inductive Deductive Synthesis: Enabling AI to Generate Formally Verified Systems

    cs.AI 2026-05 unverdicted novelty 7.0

    IDS is an agentic LLM system that incrementally synthesizes both implementation and proof for distributed key-value stores, succeeding on all 7 specs where prior agents succeeded on only 2.

  3. Certified Program Synthesis with a Multi-Modal Verifier

    cs.SE 2026-04 unverdicted novelty 7.0

    LeetProof achieves higher rates of fully certified program synthesis from natural language by using a multi-modal verifier in Lean to validate specifications via randomized testing and delegate proofs to AI tools, out...

  4. The Search for Constrained Random Generators

    cs.PL 2025-11 unverdicted novelty 7.0

    A Lean library called Palamedes uses synthesis rules from generator semantics and catamorphism-anamorphism rewriting to automatically produce correct constrained random generators.

  5. VeruSAGE: A Study of Agent-Based Verification for Rust Systems

    cs.OS 2025-12 unverdicted novelty 6.0

    LLM agents complete over 80% of tasks on a new 849-task Rust verification benchmark and over 90% on unfinished human proofs.

  6. On Reasoning-Centric LLM-based Automated Theorem Proving

    cs.SE 2026-04 unverdicted novelty 5.0

    ReCent-Prover achieves a 22.58% relative improvement over prior state-of-the-art in proved theorems on the CoqStoq benchmark by using reasoning-centric techniques under a fixed LLM invocation budget.