datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
MemoryBench
MemoryBench
MemoryBench aims to provide a standardized and extensible benchmark for evaluating memory and continual learning in LLM systems — encouraging future work toward more adaptive, feedback-driven, and efficient LLM systems.
Paper Link: https://arxiv.org/abs/2510.17281
Github: https://github.com/THUIR/MemoryBench
📢 May 26, 2026 Updated: This work has been accepted at ICML 2026 and selected for a SpotLight Paper!
📢 Dec. 8, 2025 Updated: We released an extended version… See the full description on the dataset page: https://huggingface.co/datasets/THUIR/MemoryBench.MemoryBench-Full
MemoryBench
MemoryBench aims to provide a standardized and extensible benchmark for evaluating memory and continual learning in LLM systems — encouraging future work toward more adaptive, feedback-driven, and efficient LLM systems.
Paper Link: https://arxiv.org/abs/2510.17281
Github: https://github.com/LittleDinoC/MemoryBench/
This is an extended version of MemoryBench. The training and test sets of THUIR/MemoryBench(the balanced version on which we conducted experiments in the… See the full description on the dataset page: https://huggingface.co/datasets/THUIR/MemoryBench-Full.MemoryBench-Fullmemory-bench
memory-bench v1.0.0, public release
A screened benchmark for organizational memory in agent harnesses: does a
memory system keep a rule that was stated once, drop a fact that was
superseded, and pick the right one when tiers conflict?
371 valid paired probe instances across 3 simulated
organizations, drawn from 486 probes over 612 events. Scored as pair
credit: an instance counts only if the base task and its counterfactual twin
both pass, so anything answerable from priors… See the full description on the dataset page: https://huggingface.co/datasets/notmehul/memory-bench.