InvWeaver: Deductive Feedback for Invariant Synthesis in Interacting-Loop Programs
Summary
InvWeaver is a neuro-symbolic framework that uses LLMs and deductive feedback to synthesize loop invariants for programs with multiple interacting loops, outperforming existing methods on a benchmark suite.
View Cached Full Text
Cached at: 07/08/26, 04:43 AM
# InvWeaver: Deductive Feedback for Invariant Synthesis in Interacting-Loop Programs Source: [https://arxiv.org/abs/2607.05478](https://arxiv.org/abs/2607.05478) [View PDF](https://arxiv.org/pdf/2607.05478) > Abstract:Loop invariant inference is a fundamental yet challenging problem in program verification\. Recent LLM\-aided guess\-and\-check techniques have shown strong performance on single\-loop programs, but they often struggle with programs containing multiple interacting loops\. This paper presents InvWeaver, a neuro\-symbolic framework for synthesizing invariants for such programs\. The key idea is to expose inter\-loop dependencies and propagate proof obligations through a combination of loop\-level abstraction, obligation\-guided inference, and weakest\-precondition\-based refinement\. We evaluate InvWeaver on a comprehensive benchmark suite, including a newly curated dataset derived from classic algorithms\. Experimental results show that InvWeaver substantially outperforms existing invariant inference methods, solving 72 out of 82 multi\-loop benchmark problems and maintaining strong performance on single\-loop tasks\. ## Submission history From: Guangyuan Wu \[[view email](https://arxiv.org/show-email/51479f36/2607.05478)\] **\[v1\]**Mon, 6 Jul 2026 14:36:36 UTC \(174 KB\)
Similar Articles
Inductive Deductive Synthesis: Enabling AI to Generate Formally Verified Systems
This paper presents Inductive Deductive Synthesis (IDS), an LLM-based agentic system that jointly synthesizes implementation and formal proof for distributed systems, achieving 7/7 specifications at roughly 200x faster than expert effort and 17% cheaper than state-of-the-art agents.
ImProver 2: Iteratively Self-Improving LMs for Neurosymbolic Proof Optimization
ImProver 2 is a neurosymbolic framework for automated proof optimization in Lean 4 that uses an expert-iteration pipeline and a scaffold to train a 7B-parameter model, outperforming much larger models and demonstrating that small models can effectively restructure research-level proofs.
ReaComp: Compiling LLM Reasoning into Symbolic Solvers for Efficient Program Synthesis
ReaComp compiles LLM reasoning traces into reusable symbolic program synthesizers that achieve strong accuracy on program synthesis benchmarks while eliminating LLM calls at test time, significantly reducing computational cost.
WiCER: Wiki-memory Compile, Evaluate, Refine Iterative Knowledge Compilation for LLM Wiki Systems
The paper introduces WiCER, an iterative algorithm for compiling domain knowledge into LLM Wiki systems to minimize information loss and catastrophic failure rates during knowledge distillation. It demonstrates that this approach improves upon full-context KV cache inference by preserving critical facts better than blind compilation methods.
The Imitation Game: When LLMs Learn to Reason Like Programs via Code-Centric Reasoning Data Synthesis
MIMIC is a framework that uses executable code to synthesize reasoning trajectories for LLMs, enhancing their deterministic reasoning through code-instrumented rewards and achieving improved performance on reasoning benchmarks.