Related papers: MCP-Cosmos: World Model-Augmented Agents for Compl…
World models (WMs) represent the frontier of sample-efficient reinforcement learning, but their complexity leaves many promising improvements unrealized due to the significant expertise and effort required to identify and integrate them.…
Large language models are increasingly deployed in multi-agent systems to overcome context limitations by distributing information across agents. Yet whether agents can reliably compute with distributed information, rather than merely…
This paper addresses the limitations of a single agent in task decomposition and collaboration during complex task execution, and proposes a multi-agent architecture for modular task decomposition and dynamic collaboration based on large…
The Model Context Protocol (MCP) has emerged as a standard for connecting large language models (LLMs) with external tools. However, this MCP ecosystem introduces new security risks across hosts, servers, and registries. In this paper, we…
World models are becoming central to robotic planning and control as they enable prediction of future state transitions. Existing approaches often emphasize video generation or natural-language prediction, which are difficult to ground in…
The rapid progress in embodied artificial intelligence has highlighted the necessity for more advanced and integrated models that can perceive, interpret, and predict environmental dynamics. In this context, World Models (WMs) have been…
We introduce ETOM, a five-level benchmark for evaluating multi-hop, end-to-end tool orchestration by LLM agents within a hierarchical Model-Context Protocol (MCP) ecosystem. Existing benchmarks often assess tools in isolation, overlooking…
Long-horizon embodied planning is challenging because the world does not only change through an agent's actions: exogenous processes (e.g., water heating, dominoes cascading) unfold concurrently with the agent's actions. We propose a…
In control system networks, reconfiguration of the controller when agents are leaving or joining the network is still an open challenge, in particular when operation constraints that depend on each agent's behavior must be met. Drawing our…
Large language model (LLM) agents are fundamentally constrained by context length on long-horizon tasks. We introduce Context-Folding, a framework that empowers agents to actively manage their working context. An agent can procedurally…
Although Foundation Models (FMs), such as GPT-4, are increasingly used in domains like finance and software engineering, reliance on textual interfaces limits these models' real-world interaction. To address this, FM providers introduced a…
Recent progress in generative models has stimulated significant innovations in many fields, such as image generation and chatbots. Despite their success, these models often produce sketchy and misleading solutions for complex multi-agent…
In the era of (multi-modal) large language models, most operational processes can be reformulated and reproduced using LLM agents. The LLM agents can perceive, control, and get feedback from the environment so as to accomplish the given…
Today's AI agents are built on large language models (LLMs) equipped with tools to access and modify external environments, such as corporate file systems, API-accessible platforms and websites. AI agents offer the promise of automating…
Task planning systems have been developed to help robots use human knowledge (about actions) to complete long-horizon tasks. Most of them have been developed for "closed worlds" while assuming the robot is provided with complete world…
Large language models (LLMs) have enabled remarkable advances in automated task-solving with multi-agent systems. However, most existing LLM-based multi-agent approaches rely on predefined agents to handle simple tasks, limiting the…
While Large Language Models (LLMs) have achieved remarkable performance, they remain vulnerable to jailbreak. The integration of Large Language Models (LLMs) with external tools via protocols such as the Model Context Protocol (MCP)…
Currently, agent-based simulation frameworks force the user to choose between simulations involving a large number of agents (at the expense of limited agent reasoning capability) or simulations including agents with increased reasoning…
This paper introduces \textbf{FinMCP-Bench}, a novel benchmark for evaluating large language models (LLMs) in solving real-world financial problems through tool invocation of financial model context protocols. FinMCP-Bench contains 613…
The Model Context Protocol (MCP) standardizes tool use for LLM-based agents and enable third-party servers. This openness introduces a security misalignment: agents implicitly trust tools exposed by potentially untrusted MCP servers.…