When the Consumer Is an Agent: Execution-Grounded Service-Level Agreements
cs.DC, cs.AI
Submitted: 2026-11-03
Updated: 2026-11-03
Comments: 22 pages, 2 figures. Accepted for the 24th International Conference on Service-Oriented Computing (ICSOC 2026), Springer LNCS. Followed by the companion artifact paper, accepted in the ICSOC 2026 Artifact Evaluation track. Replication package: https://doi.org/10.5281/zenodo.23000442
Code: https://github.com/OpenSLO/OpenSLO
Project page: https://onedata.github.io/charts
License: http://creativecommons.org/licenses/by/4.0/
The gist: Large language model (LLM) agents increasingly act as service consumers.
Abstract
Large language model (LLM) agents increasingly act as service consumers. They select operations and report whether a task is complete. In an asynchronous distributed service, an accepted call or immediate state read does not establish that the required state became observable by its deadline. We introduce execution-grounded completion contracts, which treat completion as a service-level outcome. An independent control plane observes a deadline-bound service-state predicate, admits completion, and directs recovery while the agent performs the task. We evaluate placement and deletion in a live multi-provider data service with heterogeneous models and an injected transfer delay. Across policies, some tasks that missed the deadline were accepted and some that met it were rejected. Under enforcement, accepted completions remained consistent with later observations; all included healthy tasks completed, and unresolved faulted tasks terminated as unverified. The results show that completion of these tasks can be governed by independent observation of service state rather than by the agent's self-assessment.
Sources
- From Confident Closing to Silent Failure: Characterizing False Success in LLM Agents
- interwhen: A Generalizable Framework for Steering Reasoning Models with Test-time Verification
- STRATUS: A Multi-agent System for Autonomous Reliability Engineering of Modern Clouds
- AgentSLA : Towards a Service Level Agreement for AI Agents
- Verify-Gated Completion as Admission Control in a Governed Multi-Agent Runtime: A Bounded Architecture Case Study
- Towards a Science of AI Agent Reliability
- AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents
- $\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains
- Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
Related papers
- Programmable Probabilistic Computer with 1,000,000 p-bits
- BatchGen: An Architecture for Scalable and Efficient Batch Inference
- Seamless Reconfiguration for DAG-BFT (Technical Report)
- ELDR: Expert-Locality-Aware Decode Routing for PD-Disaggregated MoE Serving
- iScheduler: Reinforcement Learning-Driven Continual Optimization for Large-Scale Resource Investment Problems
- TIRx: A Unified Tile Primitive ML Compiler Across Heterogeneous Backends