From Single to Multi-Granularity: How MemGAS Keeps Conversational Agents from Forgetting

The ICLR 2026 paper introduces MemGAS, a multi‑granularity memory framework that organizes dialogue history into session, turn, summary, and keyword levels, dynamically associates them with a Gaussian‑Mixture Model, selects the optimal granularity via entropy‑based routing, and achieves state‑of‑the‑art retrieval and QA performance on long‑term conversational benchmarks.

MemGASconversational agentsentropy routing

0 likes · 11 min read

From Single to Multi-Granularity: How MemGAS Keeps Conversational Agents from Forgetting

HyperAI Super Neural

Sep 19, 2025 · Artificial Intelligence

Weekly AI Paper Roundup: RL Advances, Tree‑Structured QA, and GraphRAG Breakthroughs

This article surveys five recent AI papers, covering reinforcement learning for large reasoning models, a tree‑structured table QA framework (ST‑Raptor), visual representation alignment for multimodal LLMs, GraphRAG‑based generation, and an LLM‑driven cryptographic vulnerability detector, each with key insights and links.

Reinforcement Learningcryptographic vulnerability detectiongraph retrieval

0 likes · 5 min read

Weekly AI Paper Roundup: RL Advances, Tree‑Structured QA, and GraphRAG Breakthroughs