Research & Innovation

Global: Fuzzy Category-Theoretic Planning Introduces Graded Applicability to Natural-Language PlanningA team of computer scientists announced a new framework called Fuzzy Category-theoretic Planning (FCP) in a paper posted to arXiv on…

Global: New Multi-Agent LLM System Aims to Streamline E‑Commerce Seller InsightsA research team has introduced Insight Agents, a conversational multi‑agent system designed to deliver personalized data and business insights to…

Global: Framework Provides Counterfactual Generation for LLM-Driven Autonomous ControlResearchers Amirmohammad Farzaneh, Salvatore D’Oro, and Osvaldo Simeone introduced a counterfactual reasoning framework for large language model (LLM) agents on 27 January…

Global: Iterative Retrieval Framework Enhances Accuracy of Medical Language Model Reasoning Researchers have introduced a novel agentic framework designed to improve the factual reliability of large language models used for…

Global: AI‑Driven Multi‑Modal Framework Boosts Urban Park Development MonitoringIn January 2026, researchers posted a new study on arXiv describing a large‑language‑model (LLM) agent that integrates visual, geographic and textual data…

Global: SysMoBench Benchmark Launches to Assess AI-Generated Formal SpecificationsResearchers have unveiled SysMoBench, a new benchmark aimed at evaluating large language models’ ability to automatically generate formal specifications for sizable, concurrent…

Global: On-Device LLM Agent Enables Multi‑Turn ECG DialogueResearchers led by Hyunseung Chung and colleagues submitted a paper to arXiv on January 28, 2026, describing ECG‑Agent, the first large‑language‑model (LLM) based…

Global: New Framework Aims to Close Cognitive Gap in Multimodal AI A new study released on arXiv in January 2026 introduces a training framework designed to improve how unified multimodal…

Global: Study Finds Base Language Model Shapes Reward Model Value PreferencesResearchers examined ten leading open-weight reward models (RMs) derived from various large language models (LLMs) and identified systematic differences in…

Global: Continuous Tokenization Boosts LLM-Based Recommender Systems, Study FindsResearchers have unveiled ContRec, a novel framework that integrates continuous tokens into large language model (LLM) driven recommender systems, aiming to overcome…