absorb.md

Memrefine

1 mentions across 0 people

Unknown speaker
paper · 2026-06-12
Recommended

“To this end, we then propose MemRefine, an LLM-guided framework that, since surface similarity poorly reflects factual value, uses similarity only to propose candidate pairs and defers delete, merge, and preserve decisions to an LLM judge based on factual content, iterating until the budget is met.”

MemRefine: LLM-Driven Memory Compression for Long-Term Agent Interactions ↗