# Deterministic Replay for AI Agent Systems

arXiv: https://arxiv.org/abs/2607.16200 · HTML: https://mlsanity.com/paper/2607.16200/

## Key facts

- Cited by 1 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 2 of its 20 references that are in the map.
- First posted on arXiv 30 Apr 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 2 of 2)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Talking About Large Language Models](https://mlsanity.com/paper/2212.03551/) (2022)

## Built on by (most cited first, 1 of 1)

- [Testing and Evaluation of Agentic AI Systems In Military Command and Control](https://mlsanity.com/paper/2608.20597/) (2026)

## Abstract (arXiv)

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.