← All threads

Live Software Adaptation

Methods and benchmarks for LLM agents that modify software behavior or code at runtime in response to observed failures or user needs.

4 papers

Where this stands

The written synthesis of this thread is for subscribers. Subscribe.

How this thread developed

  1. Sept 2026 · University of Kentucky, University College London

    Embedded AI agents can adapt software during live use

    Demonstrates agents that modify software logic and interfaces at runtime, opening a new direction for self-adaptive systems.

  2. 1 further paper

    Sept 2026 · Tongji University, The Hong Kong Polytechnic University

    Adaptive action chunking improves robot control by varying horizon based on prediction reliability.

    GeoAAC adaptively varies action horizons based on prediction reliability, enabling robot policies to adjust behavior in response to runtime conditions, a form of live adaptation in embodied agents.

  3. Sept 2026

    Multi-image evidence can help models repair software, but unreliably

    Introduces a multi-image software-repair benchmark and evaluates how visual access affects success rates, showing unreliability.

3 of 4 papers shown