ES‑Mem: Teaching chatbots to remember by chunking conversations into events

Kari Jaaskelainen

13 Jan 2026 — 1 min read

Why chatbots forget—and how ES‑Mem fixes it

Long chats often make assistants lose the thread. ES‑Mem, a new memory system, keeps conversations coherent by organizing them like humans do.

Breaks talks into “events.” Instead of saving every line, ES‑Mem detects natural boundaries—topics, goals, shifts—so each memory chunk stays semantically intact.
Finds the right moment faster. A hierarchical memory uses those boundaries to zoom from a big-picture summary down to the exact episode you meant.

Why it matters: fewer “Who’s Alice again?” moments, better personalization over time, and more accurate follow‑ups in long‑running chats.

In tests, ES‑Mem consistently beat common memory baselines on two benchmarks, and its event segmenter worked well on standard dialogue segmentation datasets.

Paper: https://arxiv.org/abs/2601.07582v1

Authors: Huhai Zou, Tianhao Sun, Chuanjiang He, Yu Tian, Zhenyang Li, Li Jin, Nayu Liu, Jiang Zhong, Kaiwen Wei

Paper: https://arxiv.org/abs/2601.07582v1

Register: https://www.AiFeta.com

AI NLP Chatbots LLMs Memory ConversationalAI Research

Meet GRACE: a moral governor for safer, more transparent AI

AI agents are getting powerful—so how do we make sure they do the right thing, not just the effective thing? Meet GRACE, a reason-based moral governor that keeps AI behavior aligned with human norms by separating moral reasoning from goal-driven decision-making. * Moral Module: uses deontic logic and explicit reasons

Why some fine-tuned LLMs miss phishing—and how to fix it

Not all fine-tuned LLMs spot phishing equally. A new study tests Llama 3.1 8B, Gemma 2 9B, and Mistral on high-stakes phishing detection—and uses SHAP and mechanistic interpretability to reveal why models do (or don’t) generalize. * Architecture × data diversity matters: Gemma 2 9B hits state-of-the-art performance (F1

AI that explains itself—by following the science

AI that explains itself—by following the science Black-box AI can be powerful, but it often can’t tell us why it made a decision. Concept Bottleneck Models (CBMs) try to fix that by predicting human-understandable concepts first, then the final answer. The catch: standard CBMs ignore domain-specific cause-and-effect and

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A

TL;DR: Finding reliable answers in genomics is hard. GenomAgent turns one big AI into a coordinating team of specialists—and beats the current leader by 12% on a key benchmark. Genomic facts live across many databases. Standard chatbots struggle because they can’t flexibly query those sources. GeneGPT added

Why chatbots forget—and how ES‑Mem fixes it

Read more

Meet GRACE: a moral governor for safer, more transparent AI

Why some fine-tuned LLMs miss phishing—and how to fix it

AI that explains itself—by following the science

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A