mlsanityData to 14 Oct 2026

A DbC Inspired Neurosymbolic Layer for Trustworthy Agent Design

arXiv 2508.03665 ↗First posted 5 Aug 2025cs.LG cs.AIcited by 2

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

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.

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.

Builds on

25 of 52 references.

References · 25

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  2. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  3. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  4. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  5. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  6. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 3,050
  7. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  8. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Modelscited by 886
  9. 2023Efficient Guided Generation for Large Language Modelscited by 200
  10. 2023SafetyBench: Evaluating the Safety of Large Language Modelscited by 199
  11. 2023Grammar-Constrained Decoding for Structured NLP Tasks without Finetuningcited by 197
  12. 2023A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validationcited by 93
13 more
  1. 2024Hammer: Robust Function-Calling for On-Device Language Models via Function Maskingcited by 55
  2. 2025Flexible and Efficient Grammar-Constrained Decodingcited by 43
  3. 2024Don't Just Say "I don't know"! Self-aligning Large Language Models for Responding to Unknown Questions with Explanationscited by 30
  4. 2024SymbolicAI: A framework for logic-based approaches combining generative models and solverscited by 16
  5. 2024IterAlign: Iterative Constitutional Alignment of Large Language Modelscited by 11
  6. 2024Do Large Language Models Understand Logic or Just Mimick Context?cited by 10
  7. 2024Evaluating Large Language Models in Semantic Parsing for Conversational Question Answering over Knowledge Graphscited by 7
  8. 2025PEIRCE: Unifying Material and Formal Reasoning via LLM-Driven Neuro-Symbolic Refinementcited by 7
  9. 2013Soft Contract Verificationcited by 1
  10. 2016A program logic for union boundscited by 1
  11. 2017Combining Static and Dynamic Contract Checking for Currycited by 1
  12. 2024On the Relative Completeness of Satisfaction-based Probabilistic Hoare Logic With While Loopcited by 1
  13. 2024Parameter Choice and Neuro-Symbolic Approaches for Deep Domain-Invariant Learningcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Agent Behavioral Contracts: Formal Specification and Runtime Enforcement for Reliable Autonomous AI Agentscited by 19
  2. 2026Epistemic-Probabilistic Model for Guarded Multi-Agent LLM Coordinationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025A Survey on Trustworthy LLM Agents: Threats and Countermeasures
  2. 2026FormalJudge: A Neuro-Symbolic Paradigm for Agentic Oversight
  3. 2026Verification as an Architectural Layer for LLM Agents: A V-Model Design, and a Pilot Study of Its Deterministic Core
  4. 2024The Fusion of Large Language Models and Formal Methods for Trustworthy AI Agents: A Roadmap
  5. 2026From Natural Language Policies to Executable Obligations: A Verification Harness for Dependable In-Car LLM Agents
  6. 2026Agentic Transaction: Towards ACID-Compliant Agent Systems
  7. 2026Toward Formalizing LLM-Based Agent Designs through Structural Context Modeling and Semantic Dynamics Analysis
  8. 2026Information Fidelity in Tool-Using LLM Agents: A Martingale Analysis of the Model Context Protocol