# LogAct: Enabling Agentic Reliability via Shared Logs

arXiv: https://arxiv.org/abs/2604.07988 · HTML: https://mlsanity.com/paper/2604.07988/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 6 of its 36 references that are in the map.
- First posted on arXiv 9 Apr 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 6 of 6)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations](https://mlsanity.com/paper/2312.06674/) (2023)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [Executable Code Actions Elicit Better LLM Agents](https://mlsanity.com/paper/2402.01030/) (2024)
- [LlamaFirewall: An open source guardrail system for building secure AI agents](https://mlsanity.com/paper/2505.03574/) (2025)

## Built on by (most cited first, 3 of 3)

- [Safe to Resume? Breaking Execution Continuity of Agent Execution via Rollback](https://mlsanity.com/paper/2608.29381/) (2026)
- [Where Reliability Lives: Experimental Localisation of Behavioural Properties in an Agent System](https://mlsanity.com/paper/2609.03192/) (2026)
- [Planarian: Managing Agent State with Statepoints](https://mlsanity.com/paper/2609.35366/) (2026)

## Abstract (arXiv)

Agents are LLM-driven components that can mutate environments in powerful, arbitrary ways. Extracting guarantees for the execution of agents in production environments can be challenging due to asynchrony and failures. In this paper, we propose a new abstraction called LogAct, where each agent is a deconstructed state machine playing a shared log. In LogAct, agentic actions are visible in the shared log before they are executed; can be stopped prior to execution by pluggable, decoupled voters; and recovered consistently in the case of agent or environment failure. LogAct enables agentic introspection, allowing the agent to analyze its own execution history using LLM inference, which in turn enables semantic variants of recovery, health check, and optimization. In our evaluation, LogAct agents recover efficiently and correctly from failures; debug their own performance; optimize token usage in swarms; and stop all unwanted actions for a target model on a representative benchmark with just a 3% drop in benign utility.