Cover Image

Position: A Three-Layer Probabilistic Assume-Guarantee Architecture Is Structurally Required for Safe LLM Agent Deployment

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bensalem, S., Dong, Y., Franzle, M., Huang, X., Kroger, J., Nickovic, D., Nouri, A., Roy, R., Wu, C.
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

SafeHarness: Lifecycle-Integrated Security Architecture for LLM-based Agent Deployment
by: Lin, Xixun, et al.
Published: (2026)

Cutting Corners on Uncertainty: Zonotope Abstractions for Stream-based Runtime Monitoring
by: Finkbeiner, Bernd, et al.
Published: (2026)

On the Existence of Reactive Strategies Resilient to Delay
by: Fränzle, Martin, et al.
Published: (2023)

Towards Assume-Guarantee Verification of Abilities in Stochastic Multi-Agent Systems
by: Jamroga, Wojciech, et al.
Published: (2025)

Composition and Merging of Assume-Guarantee Contracts Are Tensor Products
by: Incer, Inigo
Published: (2024)

Introduction to environmental engineering / Stefan Franzle, Bernd Markert and Simone Wunschmann
by: Franzle, Stefan
Published: (2012)

Compositional Inductive Invariant Inference via Assume-Guarantee Reasoning
by: Dardik, Ian, et al.
Published: (2025)

Pacti: Scaling Assume-Guarantee Reasoning for System Analysis and Design
by: Incer, Inigo, et al.
Published: (2023)

What, Indeed, is an Achievable Provable Guarantee for Learning-Enabled Safety Critical Systems
by: Bensalem, Saddek, et al.
Published: (2023)

Computation of Feasible Assume-Guarantee Contracts: A Resilience-based Approach
by: Monir, Negar, et al.
Published: (2025)

Early Design Exploration of Aerospace Systems Using Assume-Guarantee Contracts
by: Rouquette, Nicolas, et al.
Published: (2024)

Layer-wise Positional Bias in Short-Context Language Modeling
by: Rahimi, Maryam, et al.
Published: (2026)

Controller Synthesis of Collaborative Signal Temporal Logic Tasks for Multi-Agent Systems via Assume-Guarantee Contracts
by: Liu, Siyuan, et al.
Published: (2023)

Position: Scaling LLM Agents Requires Asymptotic Analysis with LLM Primitives
by: Meyerson, Elliot, et al.
Published: (2025)

Enumerating Safe Regions in Deep Neural Networks with Provable Probabilistic Guarantees
by: Marzari, Luca, et al.
Published: (2023)

Formal Control of New England 39-Bus Test System: An Assume-Guarantee Approach
by: Wooding, Ben, et al.
Published: (2023)

Towards the Usage of Window Counting Constraints in the Synthesis of Reactive Systems to Reduce State Space Explosion
by: Feeken, Linda, et al.
Published: (2025)

Towards the Usage of Window Counting Constraints in the Synthesis of Reactive Systems to Reduce State Space Explosion
by: Feeken, Linda, et al.
Published: (2024)

Probabilistic Soundness Guarantees in LLM Reasoning Chains
by: You, Weiqiu, et al.
Published: (2025)

Provable Guarantees for Nonlinear Feature Learning in Three-Layer Neural Networks
by: Nichani, Eshaan, et al.
Published: (2023)

A Cross-Layer Analysis of Network Antifragility with RIS-assisted Links under Jamming Attacks
by: Bensalem, Mounir, et al.
Published: (2025)

SagaLLM: Context Management, Validation, and Transaction Guarantees for Multi-Agent LLM Planning
by: Chang, Edward Y., et al.
Published: (2025)

Ask or Assume? Uncertainty-Aware Clarification-Seeking in Coding Agents
by: Edwards, Nicholas, et al.
Published: (2026)

Towards Realistic Guarantees: A Probabilistic Certificate for SmoothLLM
by: Kumarappan, Adarsh, et al.
Published: (2025)

LoRA-BAM: Input Filtering for Fine-tuned LLMs via Boxed Abstraction Monitors over LoRA Layers
by: Wu, Changshun, et al.
Published: (2025)

On the Identifiability of Sparse ICA without Assuming Non-Gaussianity
by: Ng, Ignavier, et al.
Published: (2024)

Scenario-Based Curriculum Generation for Multi-Agent Autonomous Driving
by: Brunnbauer, Axel, et al.
Published: (2024)

Jagarin: A Three-Layer Architecture for Hibernating Personal Duty Agents on Mobile
by: Kadaboina, Ravi Kiran
Published: (2026)

Rethinking AI Hardware: A Three-Layer Cognitive Architecture for Autonomous Agents
by: Chen, Li
Published: (2026)

Coordination as an Architectural Layer for LLM-Based Multi-Agent Systems
by: Nechepurenko, Maksym, et al.
Published: (2026)

StepCache: Step-Level Reuse with Lightweight Verification and Selective Patching for LLM Serving
by: Nouri, Azam
Published: (2026)

RTAMT -- Runtime Robustness Monitors with Application to CPS and Robotics
by: Yamaguchi, Tomoya, et al.
Published: (2025)

Empirical Bernstein Confidence Intervals for Kernel Smoothers: A Safe and Sharp Way to Exhaust Assumed Smoothness
by: Yuan, Zihao, et al.
Published: (2026)

Next-Token Prediction Task Assumes Optimal Data Ordering for LLM Training in Proof Generation
by: An, Chenyang, et al.
Published: (2024)

SafeAgentBench: A Benchmark for Safe Task Planning of Embodied LLM Agents
by: Yin, Sheng, et al.
Published: (2024)

Safe LLM-Controlled Robots with Formal Guarantees via Reachability Analysis
by: Hafez, Ahmad, et al.
Published: (2025)

Abstract Scene Graphs: Formalizing and Monitoring Spatial Properties of Automated Driving Functions
by: Saxena, Ishan, et al.
Published: (2025)

Model Learning for Adjusting the Level of Automation in HCPS
by: Hajnorouzi, Mehrnoush, et al.
Published: (2025)

On STPA for Distributed Development of Safe Autonomous Driving: An Interview Study
by: Nouri, Ali, et al.
Published: (2024)

Q-realign: Piggybacking Realignment on Quantization for Safe and Efficient LLM Deployment
by: Tan, Qitao, et al.
Published: (2026)