![[2602.23193] ESAA: Event Sourcing for Autonomous Agents in LLM-Based Software Engineering](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2602.23193] ESAA: Event Sourcing for Autonomous Agents in LLM-Based Software Engineering
Summary
The paper presents ESAA, an architecture for autonomous agents using event sourcing to enhance state management and execution in LLM-based software engineering.
Why It Matters
As autonomous agents evolve, they face challenges like context degradation and state management. ESAA addresses these issues by separating cognitive intentions from state mutations, improving reliability and scalability in AI applications, which is crucial for advancing software engineering practices.
Key Takeaways
- ESAA architecture separates cognitive intentions from state mutations.
- It enhances reliability through event sourcing and deterministic orchestration.
- Two case studies validate the architecture's effectiveness in multi-agent scenarios.
Computer Science > Artificial Intelligence arXiv:2602.23193 (cs) [Submitted on 26 Feb 2026] Title:ESAA: Event Sourcing for Autonomous Agents in LLM-Based Software Engineering Authors:Elzo Brito dos Santos Filho View a PDF of the paper titled ESAA: Event Sourcing for Autonomous Agents in LLM-Based Software Engineering, by Elzo Brito dos Santos Filho View PDF HTML (experimental) Abstract:Autonomous agents based on Large Language Models (LLMs) have evolved from reactive assistants to systems capable of planning, executing actions via tools, and iterating over environment observations. However, they remain vulnerable to structural limitations: lack of native state, context degradation over long horizons, and the gap between probabilistic generation and deterministic execution requirements. This paper presents the ESAA (Event Sourcing for Autonomous Agents) architecture, which separates the agent's cognitive intention from the project's state mutation, inspired by the Event Sourcing pattern. In ESAA, agents emit only structured intentions in validated JSON (this http URL or this http URL); a deterministic orchestrator validates, persists events in an append-only log (this http URL), applies file-writing effects, and projects a verifiable materialized view (this http URL). The proposal incorporates boundary contracts (this http URL), metaprompting profiles (PARCER), and replay verification with hashing (esaa verify), ensuring the immutability of completed tasks and forensic trac...
