AgileLog: A Forkable Shared Log for Agents on Data Streams

arXiv:2604.14590 · cs.DC, cs.AI · Submitted 2026-04-16 · Read on arXiv

cs.DC, cs.AI

Submitted: 2026-04-16

Updated: 2026-09-23

Code: https://github.com/tuannvm/kafka-mcpserver

Terminology

• AI Agents — 24× in this paper · explained in 2 episodes
• Abstraction — 22× in this paper · explained in 1 episode
• Core — 9× in this paper · explained in 2 episodes
• Agentic Task — 6× in this paper · explained in 1 episode
• Agentic Tasks — 6× in this paper · explained in 1 episode
• Model Context Protocol — 6× in this paper
• Model Context Protocol (MCP) — 4× in this paper · explained in 8 episodes
• Accuracy — 3× in this paper · explained in 1 episode
• Agentic AI — 3× in this paper · explained in 1 episode
• Lazy Tail Tree — 3× in this paper
• Ablation — 2× in this paper · explained in 1 episode
• Agentic Workflows — 2× in this paper · explained in 1 episode
• Consistency — 2× in this paper · explained in 3 episodes
• Trace — 2× in this paper · explained in 2 episodes
• USENIX Annual Technical Conference — 2× in this paper
• Agent Interactions — 1× in this paper · explained in 1 episode
• Agentic Architecture — 1× in this paper · explained in 1 episode
• Agentic Coding — 1× in this paper · explained in 1 episode
• Chain-of-Thought Prompting — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Multi-Agent System — 1× in this paper · explained in 6 episodes
• Nadia — 1× in this paper · explained in 2 episodes
• State Management — 1× in this paper · explained in 3 episodes
• Text-to-SQL — 1× in this paper · explained in 3 episodes

Sources

• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
• Transparent, Evaluable, and Accessible Data Agents: A Proof-of-Concept Framework
• Supporting Dynamic Agentic Workloads: How Data and Agents Interact
• Measuring Massive Multitask Language Understanding
• Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directions
• Large Language Models for Supply Chain Optimization
• Supporting Our AI Overlords: Redesigning Data Systems to be Agent-First
• CoverUp: Effective High Coverage Test Generation for Python
• Toolformer: Language Models Can Teach Themselves to Use Tools
• Safe, Untrusted, "Proof-Carrying" AI Agents: toward the agentic lakehouse
• Beyond Text-to-SQL: Autonomous Research-Driven Database Exploration with DAR
• Fork, Explore, Commit: OS Primitives for Agentic Exploration

Related papers

• iScheduler: Reinforcement Learning-Driven Continual Optimization for Large-Scale Resource Investment Problems
• SAMM: Sharded Automated Market Maker
• InferScale: GPU-Native KV Injection for Personalized LLM Serving
• Vigil: Accountable Liveness against Selective Silence
• Steelhead: Interleaving Partially Synchronous and Asynchronous Commit Rules on a Shared DAG
• Pushing CPU Speech Synthesis to the Wall: Extreme Inference Tuning under Serverless Architecture and Billing