Evo-Memory is a new streaming benchmark and evaluation framework for self-evolving memory in LLM agents, unifying over ten memory modules and introducing the ReMem pipeline for continual improvement on multi-turn and reasoning datasets.
arXiv preprint arXiv:2503.04567 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Network-controlled repeater swarms substantially raise uplink OFDM capacity, with nearest-repeater activation delivering nearly the same gains as activating all repeaters.
citing papers explorer
-
Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory
Evo-Memory is a new streaming benchmark and evaluation framework for self-evolving memory in LLM agents, unifying over ten memory modules and introducing the ReMem pipeline for continual improvement on multi-turn and reasoning datasets.
-
Capacity Analysis of OFDM Systems with a Swarm of Network-Controlled Repeaters
Network-controlled repeater swarms substantially raise uplink OFDM capacity, with nearest-repeater activation delivering nearly the same gains as activating all repeaters.