Inductive Deductive Synthesis: Enabling AI to Generate Formally Verified Systems
Quick Answer
This paper shows that Inductive Deductive Synthesis (IDS) is a novel AI approach that achieves formal verification of distributed systems, completing all 7 specifications in 6.8 hours at an average cost of $106, outperforming expert efforts by 200x.
Quick Take
This -based system not only synthesizes implementation and proof but also learns from failures, yielding implementations up to 3x faster than existing verified systems.
Key Points
- IDS synthesizes implementation and proof jointly, learning from previous failures.
- Achieves 7/7 specifications for distributed key-value stores in 6.8 hours.
- Costs an average of $106 per specification, significantly cheaper than expert efforts.
- Outperforms state-of-the-art agents by 200x in speed and 17% in cost.
- Implements solutions up to 3x faster than previously published verified systems.
Paper Resources
Article Content
From source RSS / original summaryarXiv:2605. 23109v1 Announce Type: new Abstract: AI agents increasingly excel at generating, testing, and refining code. However, they fall short on tasks requiring formal guarantees of full coverage that testing alone cannot provide. Distributed systems are a prime example: properties such as consistency between reads and writes must hold under every possible interleaving of events. Mechanized formal verification can guarantee such correctness, but typically demands months to years of expert effort.
As evidence, even SOTA coding agents (Codex with GPT-5. 4 and Claude Code with Opus 4. 6) succeed on only 2/7 distributed key-value-store specifications. In this paper, we present the first effective approach to addressing this gap, Inductive Deductive Synthesis (IDS), which jointly and incrementally synthesizes implementation and proof, and learns from failed attempts to systematically try promising strategies. Built as an agentic system, IDS achieves 7/7 in about 6.
8 hours and $106 per spec on average, roughly 200x faster than expert effort and 17% cheaper than SOTA agents. IDS further incorporates performance feedback into the same loop, yielding implementations up to 3x faster than published verified systems.
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising
HOBA (Hierarchical On-policy Bidding Agents) is a novel hierarchical reinforcement learning framework that enhances online advertising bidding systems by improving adaptability and reducing hyperparameter tuning costs. It utilizes a for hyperparameter inference, a SARSA agent for expert model selection, and a dynamic expert pool for bid execution, achieving a +3.6% increase in target cost during large-scale deployment and outperforming state-of-the-art baselines on AuctionNet.