The paper introduces LongDS, a new benchmark for long-horizon, multi-turn data analysis, demonstrating that current AI agents struggle significantly with maintaining and updating complex analytical st…

The paper introduces Grounded Agentic Interaction Synthesis (GAIS), a framework that generates high-quality, diverse, and complex agentic training data by anchoring tasks to real-world protocols, sign…

The paper introduces LingBot-World 2.0, an advanced version of a language model with unbounded interaction horizon, rapid response time, diverse interactive elements, and agentic harness integration.

Restructuring the communication topology among robots provides significantly greater performance gains in multi-robot coordination than simply increasing the size of the onboard AI models, given fixed…

The paper proposes TCP-MCP, a co-evolution framework that jointly optimizes agent prompts and communication topologies to design highly efficient and effective multi-agent systems.

The paper introduces MCP-Persona, a novel benchmark designed to evaluate LLM agents' performance on real-world, personalized applications using the Model Context Protocol (MCP), revealing that current…

The paper argues that for embodied AI to be safe and effective, world models must be physically viable, requiring a structural shift from mere observation prediction to representing the underlying phy…

The paper proves XNLP-hardness of Directed Edge Geography and Undirected Edge Geography when parameterized by pathwidth, and shows their fixed-parameter tractability when parameterized by treewidth an…

This paper proposes shifting the focus of AI research from isolated computational outputs to interaction dynamics, establishing 'Interaction-Centered Intelligence' as the primary framework for underst…

This paper presents a software ecosystem enabling consistent development environments for running workflows across diverse hardware platforms.

This paper proposes an efficient human intervention mechanism, Deep Interaction, for correcting reasoning errors in large language models, achieving over 25% improvement in correction success rate and…

This paper explores tools for control engineers to design socio-technical systems in a more principled and ethical manner, using feedback optimization, control of Markov decision processes, and model…

This paper introduces the Goal-Oriented Dialogue Runtime (GODR), a framework-neutral design pattern for managing complex, multi-domain, interruptible conversations with multiple interdependent objecti…

This paper systematically studies the potential of prompt optimization in multi-agent systems (MAS) across various setups, revealing significant gains but also open challenges.

The paper introduces TaskWeave, a hierarchical agentic framework that successfully simulates long-horizon organizational dynamics by treating coordination as a memory-centered problem, demonstrating t…

Plover is a plan-centric vision-based GUI automation system that externalizes task plans and replanning as inspectable artifacts, enabling explicit supervision and localized correction.

The XAIxArts workshop explores the operationalisation of Explainable AI in the Arts, focusing on diversity, ideation, and resource development.

This paper introduces a controlled environment to study multi-turn long-horizon planning ability acquisition, shaping, and integration in foundation model agents.

SIRI introduces a self-internalizing reinforcement learning framework that allows LLM agents to autonomously discover and integrate reusable skills directly into their core policy, significantly impro…