LIMBO: Lifelong Inference-Time Memory and Budget Optimization for LLM Agents
LIMBO is introduced, the first online framework to the authors' knowledge that treats memory as a controllable inference-time resource and jointly optimizes memory strategy and inference budget for each incoming task, and learns this allocation online in a single pass.
Siddharth Sharma, N. Pandey, Onat Gungor et al.
· 1 citation