FIELD NOTES TOPIC
artificial intelligence research
3 notes, newest first.
SPADE: Self-Play in Adaptive Synthetic Executable Environments
The paper introduces SPADE (Self-Play in Adaptive Synthetic Executable Environments), a framework that allows a language model to design and learn in its own self-generated, diverse, adaptive environments. This…
AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents
The researchers introduce a new contract system for long-term learning machine (LLM) agents that limits the memory of each decision to a fresh user message, assembled by typed retrieval. They test this contract in the…
Advancing Omnimodal Embodied Agents from Isolated Skills to Everyday Physical Autonomy
The paper presents OmniAct, a framework for building persistent embodied agents that can operate in unstructured environments. The framework aims to integrate various tools from both cyber and physical domains, handle…
