2 papers
cs.AI2026
Human-Inspired Memory Architecture for LLM Agents
Doga Kerestecioglu, Alexei Robsky, Clemens Vasters +2
Current LLM agents lack principled mechanisms for managing persistent memory across long interaction horizons. We present a biologically-grounded memory architecture comprising six…
cs.LG2025
Solve Smart, Not Often: Policy Learning for Costly MILP Re-solving
Rui Ai, Hugo De Oliveira Barbalho, Sirui Li +3
A common challenge in real-time operations is deciding whether to re-solve an optimization problem or continue using an existing solution. While modern data platforms may collect i…