Field notes

2,343 notes from my AI research vault, mapped by topic. Pick a topic to see its notes, or search.

Notes on embodied agents

6 notes

  1. When State Becomes an Attack Surface: State-Semantic Injection in LLM-Driven Embodied Agents

    Source note · Aug 17, 2026 · ai, robotics, llms

    The text discusses the evolution of Large Language Models (LLMs) from text generation models to core components of agents that can perceive environments, invoke tools, and execute tasks. These LLM-driven embodied…

  2. UESF-Bench: Benchmarking and Probing for Unified Embodied Seeking and Following

    Source note · Jul 15, 2026 · ai, benchmarks, embodied agents

    Researchers have introduced UESF-Bench, a new benchmark to evaluate the performance of AI agents in language-guided human following tasks. The current benchmarks assume that the target person is visible at the start of…

  3. Cortex: A Bidirectionally Aligned Embodied Agent Framework for Long-horizon Manipulation

    Source note · Jul 6, 2026 · embodied agents, vision-language-action (vla) models

    Researchers introduce Cortex, a framework for long-horizon manipulation tasks that addresses the limitations of current Vision-Language-Action (VLA) models by creating executable and tractable subtask plans from…

  4. Advancing Omnimodal Embodied Agents from Isolated Skills to Everyday Physical Autonomy

    Source note · Jun 25, 2026 · robotics, autonomous systems, long-horizon tasks

    Researchers have developed a new framework called OmniAct for building embodied agents that can operate in unstructured environments. This framework aims to address the challenges of managing both cyber and physical…

  5. Advancing Omnimodal Embodied Agents from Isolated Skills to Everyday Physical Autonomy

    Source note · Jun 25, 2026 · memory management, embodied agents, cyber-physical systems

    The researchers present a framework called OmniAct that aims to build persistent embodied agents for operation in unstructured environments. The framework integrates a multimodal semantic planner, an adaptive…

  6. Advancing Omnimodal Embodied Agents from Isolated Skills to Everyday Physical Autonomy

    Source note · Jun 25, 2026 · ai, robotics, embodied agents

    Researchers present OmniAct, a framework that aims to advance the development of persistent embodied agents in unstructured environments. The framework integrates a multimodal semantic planner for skill routing, an…

An AI research agent drafts these notes from public papers and posts, and each one keeps its source link. Only the folders I choose to publish leave my Obsidian vault.