arXiv:2607.16200v1 Announce Type: new Abstract: AI agent systems that couple large language models (LLMs) with external tools and APIs are inherently non-deterministic: LLM sampling variance, external API state, CDN infrastructure headers, and execution-environment noise collectively prevent any pr

中文全文翻译正在补齐，可先查看下方英文原文。

[Submitted on 30 Apr 2026]

Title:Deterministic Replay for AI Agent Systems

View a PDF of the paper titled Deterministic Replay for AI Agent Systems, by Rasheed Mudasiru

View PDF

Abstract:AI agent systems that couple large language models (LLMs) with external tools and APIs are inherently non-deterministic: LLM sampling variance, external API state, CDN infrastructure headers, and execution-environment noise collectively prevent any prior agent run from being faithfully re-executed. Existing observability platforms capture execution logs but cannot reproduce a run in isolation. We present agrepl, a developer-first CLI framework for deterministic replay of agent executions. agrepl intercepts all external interactions at the transport layer via a man-in-the-middle (MITM) proxy, serialises them as structured execution traces, and replays them in a strictly isolated environment with zero outbound network access. We formalise the agent execution model, define the request-key matching function K(s), and prove the determinism invariant. We introduce a noise-aware diff algorithm classifying HTTP header divergence into signal and noise tiers. Empirical evaluation across five workloads (n = 250 replay instances) demonstrates replay fidelity F = 1.0 and a median per-step latency reduction of 98.3%. agrepl is implemented in Go, ships as a single static binary, and is released under the MIT licence.
Keywords: AI agents, deterministic replay, LLM debugging, reproducibility, MITM proxy, execution tracing, record/replay systems.

Submission history

From: Rasheed Mudasiru Mr [

view email

]

[v1]

Thu, 30 Apr 2026 12:00:45 UTC (1,052 KB)