mlsanityData to 14 Oct 2026

ATA: A Neuro-Symbolic Approach to Implement Autonomous and Trustworthy Agents

arXiv 2510.16381 ↗First posted 18 Oct 2025cs.CL cs.AIcited by 2

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

Abstract (arXiv)

Large Language Models (LLMs) have demonstrated impressive capabilities, yet their deployment in high-stakes domains is hindered by inherent limitations in trustworthiness, including hallucinations, instability, and a lack of transparency. To address these challenges, we introduce a generic neuro-symbolic approach, which we call Autonomous Trustworthy Agents (ATA). The core of our approach lies in decoupling tasks into two distinct phases: Offline knowledge ingestion and online task processing. During knowledge ingestion, an LLM translates an informal problem specification into a formal, symbolic knowledge base. This formal representation is crucial as it can be verified and refined by human experts, ensuring its correctness and alignment with domain requirements. In the subsequent task processing phase, each incoming input is encoded into the same formal language. A symbolic decision engine then utilizes this encoded input in conjunction with the formal knowledge base to derive a reliable result. Through an extensive evaluation on a complex reasoning task, we demonstrate that a concrete implementation of ATA is competitive with state-of-the-art end-to-end reasoning models in a fully automated setup while maintaining trustworthiness. Crucially, with a human-verified and corrected knowledge base, our approach significantly outperforms even larger models, while exhibiting perfect determinism, enhanced stability against input perturbations, and inherent immunity to prompt injection attacks. By generating decisions grounded in symbolic reasoning, ATA offers a practical and controllable architecture for building the next generation of transparent, auditable, and reliable autonomous agents.

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 26 of its 32 references that are in the map. First posted on arXiv 18 Oct 2025.

Builds on

26 of 32 references.

References · 26

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  4. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  5. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,796
  6. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  7. 2024A Survey on Large Language Models for Code Generationcited by 658
  8. 2023Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignmentcited by 401
  9. 2025The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexitycited by 302
  10. 2025Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Modelscited by 293
  11. 2025Why Language Models Hallucinatecited by 220
  12. 2025ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoningcited by 201
14 more
  1. 2023LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Proverscited by 168
  2. 2024Automatic and Universal Prompt Injection Attacks against Large Language Modelscited by 119
  3. 2024Non-Determinism of "Deterministic" LLM Settingscited by 92
  4. 2024Large Language Models Can Solve Real-World Planning Rigorously with Formal Verification Toolscited by 47
  5. 2025LLMs for Explainable AI: A Comprehensive Surveycited by 45
  6. 2025A Comprehensive Survey on the Trustworthiness of Large Language Models in Healthcarecited by 27
  7. 2024Large Language Models are Biased Because They Are Large Language Modelscited by 26
  8. 2024Logic-of-Thought: Injecting Logic into Contexts for Full Reasoning in Large Language Modelscited by 23
  9. 2024Proof of Thought : Neurosymbolic Program Synthesis allows Robust and Interpretable Reasoningcited by 19
  10. 2025The Order Effect: Investigating Prompt Sensitivity to Input Order in LLMscited by 19
  11. 2024Establishing and Evaluating Trustworthy AI: Overview and Research Challengescited by 12
  12. 2024A Survey on Verification and Validation, Testing and Evaluations of Neurosymbolic Artificial Intelligencecited by 10
  13. 2025Grammars of Formal Uncertainty: When to Trust LLMs in Automated Reasoning Taskscited by 10
  14. 2025Reasoning LLMs are Wandering Solution Explorerscited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Ontology-Constrained Neural Reasoning in Enterprise Agentic Systems: A Neurosymbolic Architecture for Domain-Grounded AI Agentscited by 3
  2. 2026Beyond Memory Majority: Latent-Source Reasoning for Multi-Agent Memory Arbitrationcited by 3

Similar, not cited

Close in wording, no citation either way

  1. 2026FormalJudge: A Neuro-Symbolic Paradigm for Agentic Oversight
  2. 2023Building Trustworthy NeuroSymbolic AI Systems: Consistency, Reliability, Explainability, and Safety
  3. 2026Moxia: A Trust-First Neuro-Symbolic Execution Architecture for Self-Explaining Mathematical Reasoning
  4. 2026AGEL-Comp: A Neuro-Symbolic Framework for Compositional Generalization in Interactive Agents
  5. 2022MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning
  6. 2023Enabling High-Level Machine Reasoning with Cognitive Neuro-Symbolic Systems
  7. 2024DANA: Domain-Aware Neurosymbolic Agents for Consistency and Accuracy
  8. 2024The Fusion of Large Language Models and Formal Methods for Trustworthy AI Agents: A Roadmap