# AgileLog: A Forkable Shared Log for Agents on Data Streams

arXiv: https://arxiv.org/abs/2604.14590 · HTML: https://mlsanity.com/paper/2604.14590/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 16 of its 121 references that are in the map.
- First posted on arXiv 16 Apr 2026.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 16 of 16)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directions](https://mlsanity.com/paper/2503.23278/) (2025)
- [Automated Unit Test Improvement using Large Language Models at Meta](https://mlsanity.com/paper/2402.09171/) (2024)
- [Large Language Models for Supply Chain Optimization](https://mlsanity.com/paper/2307.03875/) (2023)
- [CoverUp: Effective High Coverage Test Generation for Python](https://mlsanity.com/paper/2403.16218/) (2024)
- [Supporting Our AI Overlords: Redesigning Data Systems to be Agent-First](https://mlsanity.com/paper/2509.00997/) (2025)
- [No Provisioned Concurrency: Fast RDMA-codesigned Remote Fork for Serverless Computing](https://mlsanity.com/paper/2203.10225/) (2022)
- [Safe, Untrusted, "Proof-Carrying" AI Agents: toward the agentic lakehouse](https://mlsanity.com/paper/2510.09567/) (2025)
- [Fork, Explore, Commit: OS Primitives for Agentic Exploration](https://mlsanity.com/paper/2602.08199/) (2026)
- [Supporting Dynamic Agentic Workloads: How Data and Agents Interact](https://mlsanity.com/paper/2512.09548/) (2025)
- [Beyond Text-to-SQL: Autonomous Research-Driven Database Exploration with DAR](https://mlsanity.com/paper/2512.14622/) (2025)
- [Transparent, Evaluable, and Accessible Data Agents: A Proof-of-Concept Framework](https://mlsanity.com/paper/2509.24127/) (2025)

## Abstract (arXiv)

In modern data-streaming systems, alongside traditional programs, a new type of entity has emerged that can interact with streaming data: AI agents. Unlike traditional programs, AI agents use LLM reasoning to accomplish high-level tasks specified in natural language over streaming data. Unfortunately, current streaming systems cannot fully support agents: they lack the fundamental mechanisms to avoid the performance interference caused by agentic tasks and to safely handle agentic writes. We argue that the shared log, the core abstraction underlying streaming data, must support creating forks of itself, and that such a forkable shared log serves as a great substrate for agents acting on streaming data. We propose AgileLog, a new shared log abstraction that provides novel forking primitives for agentic use cases. We design Bolt, a system that implements the AgileLog abstraction. Bolt uses many novel techniques to make forks cheap and to provide logical and performance isolation.