Towards Tackling Application Logic Flaws through Autonomous Formal-Logic Modeling and Automated Reasoning

arXiv:2609.10537 · cs.CR · Submitted 2026-09-09 · Read on arXiv

cs.CR

Submitted: 2026-09-09

Updated: 2026-10-13

Comments: 13 pages, 3 figures, 3 tables

Code: https://github.com/NickWaterton/Roomba980-Python

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Verifier — 4× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• Formal Black-Box Analysis of Routing Protocol Implementations
• eXtreme Modelling in Practice
• Efficient Guided Generation for Large Language Models
• GoEX: Perspectives and Designs Towards a Runtime for Autonomous LLM Applications
• Grammar-Constrained Decoding for Structured NLP Tasks without Finetuning
• FANTAstic SEquences and Where to Find Them: Faithful and Efficient API Call Generation through State-tracked Constrained Decoding and Reranking
• Let Me Speak Freely? A Study on the Impact of Format Restrictions on Performance of Large Language Models
• Grammar-Aligned Decoding
• Automata-based constraints for language model decoding
• Sketch-Guided Constrained Decoding for Boosting Blackbox Large Language Models without Logit Access
• IterGen: Iterative Semantic-aware Structured LLM Generation with Backtracking
• Formal-LLM: Integrating Formal Language and Natural Language for Controllable LLM-based Agents
• XGrammar: Flexible and Efficient Structured Generation Engine for Large Language Models
• JSONSchemaBench: A Rigorous Benchmark of Structured Outputs for Language Models
• Gorilla: Large Language Model Connected with Massive APIs
• Unleashing the Power of LLM to Infer State Machine from the Protocol Implementation
• Automated Proof Generation for Rust Code via Self-Evolution
• Ranking LLM-Generated Loop Invariants for Program Verification
• Towards Neural Synthesis for SMT-Assisted Proof-Oriented Programming

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs