TL;DR
DynaGraph-LLM is introduced, a novel neuro-symbolic architecture that endows LLMs with a dynamic, persistent, and structured memory and implements a Dual-Phase Memory Consolidation process, inspired by hippocampal-neocortical interactions in the human brain, to refine and abstract knowledge over time.
MulTR, a comprehensive benchmark designed for multi-answer temporal reasoning from long unstructured contexts, is introduced, designed to systematically decouple temporal reasoning capabilities from the uncertainty of the number of answers.
RUMBA (Russian User Memory BenchmArk) is introduced - a new benchmark for long-term conversational memory that provides a fine-grained taxonomy of memory-centric question types and a unified methodology accounting for semantic type, session scope, temporal reasoning, and the explicitness of temporal expressions.
TrajWiki is proposed, a trajectory-based memory framework for long-horizon conversational agents that improves long-horizon dialogue performance across both open-source and closed-source LLM backbones, while providing greater interpretability and diagnostic visibility into memory evolution, retrieval failures, and answ...
A novel framework, \textit{GAMER}~(Graph-based Action-centric Memory with Episodic Reasoning), that bridges the gap between inference scaling and episodic memory by decoupling the memory mechanism from LLMs.
The results suggest that the accuracy--cost trade-off of long-term agent memory depends not only on what information is retained, but also on the granularity at which it is consolidated, and that the accuracy--cost trade-off of long-term agent memory depends not only on what information is retained, but also on the gra...
This work proposes ForgetBench, a benchmark designed to systematically characterize forgetting behavior in LLMs under continual knowledge editing, and introduces two complementary evaluation paradigms, namely concept-based QA and scenario-based QA, to disentangle isolated factual retention from structured relational kn...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
