Beyond Prompt Engineering: Neuro-Symbolic-Causal Architecture for Robust Multi-Objective AI Agents

arXiv 2510.23682 ↗First posted 27 Oct 2025cs.LG cs.AI cs.LOcited by 0

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

Abstract (arXiv)

Large language models show promise as autonomous decision-making agents, yet their deployment in high-stakes domains remains fraught with risk. Without architectural safeguards, LLM agents exhibit catastrophic brittleness: identical capabilities produce wildly different outcomes depending solely on prompt framing. We present Chimera, a neuro-symbolic-causal architecture that integrates three complementary components - an LLM strategist, a formally verified symbolic constraint engine, and a causal inference module for counterfactual reasoning. We benchmark Chimera against baseline architectures (LLM-only, LLM with symbolic constraints) across 52-week simulations in a realistic e-commerce environment featuring price elasticity, trust dynamics, and seasonal demand. Under organizational biases toward either volume or margin optimization, LLM-only agents fail catastrophically (total loss of 99K in volume scenarios) or destroy brand trust (-48.6% in margin scenarios). Adding symbolic constraints prevents disasters but achieves only 43-87% of Chimera's profit. Chimera consistently delivers the highest returns (1.52M and 1.96M respectively, some cases +2.2M) while improving brand trust (+1.8% and +10.8%, some cases +20.86%), demonstrating prompt-agnostic robustness. Our TLA+ formal verification proves zero constraint violations across all scenarios. These results establish that architectural design not prompt engineering determines the reliability of autonomous agents in production environments. We provide open-source implementations and interactive demonstrations for reproducibility.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 14 of its 29 references that are in the map. First posted on arXiv 27 Oct 2025.

Builds on

14 of 29 references.

References · 14

2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,634
2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,880
2015Estimation and Inference of Heterogeneous Treatment Effects using Random Forestscited by 597
2023Augmented Language Models: a Surveycited by 398
2015Neural Module Networkscited by 375
2020Neurosymbolic AI: The 3rd Wavecited by 253
2017Learning Explanatory Rules from Noisy Datacited by 210
2017End-to-End Differentiable Provingcited by 159
2015Doubly Robust Policy Evaluation and Optimizationcited by 158
2018Orthogonal Random Forest for Causal Inferencecited by 51

2 more

2018Deconfounding Reinforcement Learning in Observational Settingscited by 36
2019Neural Markov Logic Networkscited by 27

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way