ASPIRE is a continual learning system that autonomously writes and refines robot control programs in a code-as-policy paradigm, discovering transferable skills and surpassing prior methods on various…

This paper introduces Retriever, an asynchronous decision model and runtime system for building long-horizon robot agents with explicit clock and input-consumption semantics.

The paper introduces Graph-as-Policy (GaP), a multi-agent coding harness for Variational Automation tasks that generates directed computation graphs and improves success rates and throughput through i…

This paper proposes using offline reinforcement learning (RL) as an efficient alternative to online RL for post-training code-generating LLMs, demonstrating its effectiveness, especially for smaller m…

The paper proposes Fuzzy-Function Programming and introduces Program-as-Weights (PAW), a compact, locally-executable neural artifact for everyday programming tasks.

This paper provides a systematic survey of ROS 2 middleware and identifies architectural limits through three dimensions: Space, Time, and State.

The paper introduces RoboWits, a new bi-manual robotic benchmark designed to test a robot's cognitive reasoning and adaptability to unexpected challenges, revealing that current Vision-Language-Action…

The paper introduces Grid Programs, a novel, Turing-complete model of computation where programs are two-dimensional arrangements of instructions, fundamentally departing from linear code structures.

The paper introduces a data-centric optimization pipeline to improve coding agents' ability to interact with a branching lakehouse, showing significant accuracy gains by treating agent evaluation as a…

This paper revisits N-version programming with AI coding agents and finds substantial common-mode failures but also practical benefits.

The paper introduces CHECKMATE, a novel framework that uses code evolution to automatically generate and optimize algorithms for complex combinatorial problems, outperforming state-of-the-art solvers.

This paper introduces TRIM, an algorithm that minimizes redundant edits in AI-generated code, called CodeSlop, by minimizing agent trajectories, reducing CodeSlop by 17.9%-32.9% with negligible perfor…

The paper demonstrates that using Reinforcement Learning from Verifiable Rewards (RLVR) significantly improves small language models' functional correctness in code generation, particularly when combi…

This paper proposes SkillOpt-Lite, a minimal viable pipeline for skill optimization in autonomous agents, which accelerates convergence and outperforms full SkillOpt.

This paper presents a robot-agnostic compliant-control framework with standardized interfaces for ROS control ecosystem, enabling reusable infrastructure for various manipulators and diverse compliant…

The paper proposes a novel attack paradigm demonstrating how compromising a single robot in an LLM-controlled multi-robot system can rapidly propagate malicious intent to cause coordinated unsafe acti…