# A DbC Inspired Neurosymbolic Layer for Trustworthy Agent Design

arXiv: https://arxiv.org/abs/2508.03665 · HTML: https://mlsanity.com/paper/2508.03665/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 25 of its 52 references that are in the map.
- First posted on arXiv 5 Aug 2025.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 25 of 25)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [Graph of Thoughts: Solving Elaborate Problems with Large Language Models](https://mlsanity.com/paper/2308.09687/) (2023)
- [Efficient Guided Generation for Large Language Models](https://mlsanity.com/paper/2307.09702/) (2023)
- [SafetyBench: Evaluating the Safety of Large Language Models](https://mlsanity.com/paper/2309.07045/) (2023)
- [Grammar-Constrained Decoding for Structured NLP Tasks without Finetuning](https://mlsanity.com/paper/2305.13971/) (2023)
- [A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation](https://mlsanity.com/paper/2305.11391/) (2023)
- [Hammer: Robust Function-Calling for On-Device Language Models via Function Masking](https://mlsanity.com/paper/2410.04587/) (2024)
- [Flexible and Efficient Grammar-Constrained Decoding](https://mlsanity.com/paper/2502.05111/) (2025)
- [Don't Just Say "I don't know"! Self-aligning Large Language Models for Responding to Unknown Questions with Explanations](https://mlsanity.com/paper/2402.15062/) (2024)
- [SymbolicAI: A framework for logic-based approaches combining generative models and solvers](https://mlsanity.com/paper/2402.00854/) (2024)
- [IterAlign: Iterative Constitutional Alignment of Large Language Models](https://mlsanity.com/paper/2403.18341/) (2024)
- [Do Large Language Models Understand Logic or Just Mimick Context?](https://mlsanity.com/paper/2402.12091/) (2024)
- [Evaluating Large Language Models in Semantic Parsing for Conversational Question Answering over Knowledge Graphs](https://mlsanity.com/paper/2401.01711/) (2024)
- [PEIRCE: Unifying Material and Formal Reasoning via LLM-Driven Neuro-Symbolic Refinement](https://mlsanity.com/paper/2504.04110/) (2025)
- [Soft Contract Verification](https://mlsanity.com/paper/1307.6239/) (2013)
- [A program logic for union bounds](https://mlsanity.com/paper/1602.05681/) (2016)
- [Combining Static and Dynamic Contract Checking for Curry](https://mlsanity.com/paper/1709.04816/) (2017)
- [On the Relative Completeness of Satisfaction-based Probabilistic Hoare Logic With While Loop](https://mlsanity.com/paper/2406.16054/) (2024)
- [Parameter Choice and Neuro-Symbolic Approaches for Deep Domain-Invariant Learning](https://mlsanity.com/paper/2410.06235/) (2024)

## Built on by (most cited first, 2 of 2)

- [Agent Behavioral Contracts: Formal Specification and Runtime Enforcement for Reliable Autonomous AI Agents](https://mlsanity.com/paper/2602.22302/) (2026)
- [Epistemic-Probabilistic Model for Guarded Multi-Agent LLM Coordination](https://mlsanity.com/paper/2609.29366/) (2026)

## Abstract (arXiv)

Generative models, particularly Large Language Models (LLMs), produce fluent outputs yet lack verifiable guarantees. We adapt Design by Contract (DbC) and type-theoretic principles to introduce a contract layer that mediates every LLM call. Contracts stipulate semantic and type requirements on inputs and outputs, coupled with probabilistic remediation to steer generation toward compliance. The layer exposes the dual view of LLMs as semantic parsers and probabilistic black-box components. Contract satisfaction is probabilistic and semantic validation is operationally defined through programmer-specified conditions on well-typed data structures. More broadly, this work postulates that any two agents satisfying the same contracts are functionally equivalent with respect to those contracts.