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
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.
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.
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