• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    AI

    Paper Proposes Runtime-Independent Persistent Agents

    Zhenyu Zhao and Roy Zhao outline an architecture for agents that preserve identity and memory across changing models and servers.

    EL
    2 Sources, ,

    TLDR

    AI researcher Elvis Saravia highlighted the paper Runtime-Independent Persistent Agents. Its authors argue that agents are typically described by the model and harness running at one moment. That framing works for a single session yet leaves long-lived agents underspecified when they switch models or servers over months. The work presents a runtime-independent architecture meant to keep identity, memory, and code intact regardless of the underlying model, harness, or host.

    Combined views

    13.7K

    2 Sources, first seen 28d ago

    Combined views

    13.7K

    2 Sources, first seen 28d ago

    174 likes
    28d ago
    first seen 28d ago
    174 likes
    30 comments
    205 saves
    31 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    30 comments
    205 saves
    31 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet

    2 Sources

    @omarsar0What a super interesting paper this one is. They propose an architecture for agents that outlive their model, harness and host. Today we describe an agent by whatever model and harness it happens to run on. That works for a single session. It says very little about an agent that runs for months and gets moved to a new model, a new harness, or a new machine along the way. The paper splits an agent in two. One half is the agent itself, and it persists. Its identity, its private memory, and its own code with version history. The other half is plumbing you can replace. The model doing the reasoning, the harness running it, the server hosting it, and the ways people reach it such as chat, an API, or a UI. Swap the plumbing and you have moved the agent rather than built a new one, as long as the handoff is authorized and keeps the record of where it came from. The handoff is six steps. Pause the agent, save its state, check the save is valid, attach it to the new setup, load the state back, then let it run again. They ran the frozen public release on a clean machine and it passed 833 core tests plus 92 more for providers and libraries. They also swapped model versions, interfaces and physical hosts on live deployments. The authors are careful about what this proves. It shows you can move an agent without breaking it mechanically. Whether the agent still behaves like itself afterwards is a separate question. Paper: https://arxiv.org/abs/2609.00546 Chat with Paper: https://academy.dair.ai/papers/runtime-independent-persistent-agents-preserving-identity-memory-and-code-across-2609.00546

    2 Sources

    @omarsar0What a super interesting paper this one is. They propose an architecture for agents that outlive their model, harness and host. Today we describe an agent by whatever model and harness it happens to run on. That works for a single session. It says very little about an agent that runs for months and gets moved to a new model, a new harness, or a new machine along the way. The paper splits an agent in two. One half is the agent itself, and it persists. Its identity, its private memory, and its own code with version history. The other half is plumbing you can replace. The model doing the reasoning, the harness running it, the server hosting it, and the ways people reach it such as chat, an API, or a UI. Swap the plumbing and you have moved the agent rather than built a new one, as long as the handoff is authorized and keeps the record of where it came from. The handoff is six steps. Pause the agent, save its state, check the save is valid, attach it to the new setup, load the state back, then let it run again. They ran the frozen public release on a clean machine and it passed 833 core tests plus 92 more for providers and libraries. They also swapped model versions, interfaces and physical hosts on live deployments. The authors are careful about what this proves. It shows you can move an agent without breaking it mechanically. Whether the agent still behaves like itself afterwards is a separate question. Paper: https://arxiv.org/abs/2609.00546 Chat with Paper: https://academy.dair.ai/papers/runtime-independent-persistent-agents-preserving-identity-memory-and-code-across-2609.00546