相关论文: WebGraphEval: Multi-Turn Trajectory Evaluation for…
The rapid deployment of AI agents in commercial settings has outpaced the development of evaluation methodologies that reflect production realities. Existing benchmarks measure agent capabilities through retrospectively curated tasks with…
Simultaneous trajectory prediction for multiple heterogeneous traffic participants is essential for the safe and efficient operation of connected automated vehicles under complex driving situations in the real world. The multi-agent…
Mobile agents can autonomously complete user-assigned tasks through GUI interactions. However, existing mainstream evaluation benchmarks, such as AndroidWorld, operate by connecting to a system-level Android emulator and provide evaluation…
Existing web agent benchmarks have largely converged on short, single-site tasks that frontier models are approaching saturation on. However, real world web use consists of long-horizon, multi-site workflows. Common web navigation tasks,…
While the modeling of pair-wise relations has been widely studied in multi-agent interacting systems, its ability to capture higher-level and larger-scale group-wise activities is limited. In this paper, we propose a group-aware relational…
As language models (LMs) are used to build autonomous agents in real environments, ensuring their adversarial robustness becomes a critical challenge. Unlike chatbots, agents are compound systems with multiple components taking actions,…
Multiagent systems consist of agents that locally exchange information through a physical network subject to a graph topology. Current control methods for networked multiagent systems assume the knowledge of graph topologies in order to…
Web Agents are increasingly deployed to perform complex tasks in real web environments, yet their security evaluation remains fragmented and difficult to standardize. We present WebTrap Park, an automated platform for systematic security…
Recent years, multimodal models have made remarkable strides and pave the way for intelligent browser use agents. However, when solving tasks on real world webpages in multi-turn, long-horizon trajectories, current agents still suffer from…
Graphical User Interface (GUI) agents can automate complex tasks across digital environments, but their development is hindered by the scarcity of high-quality trajectory data for training. Existing approaches rely on expensive human…
Deep research systems are widely used for multi-step web research, analysis, and cross-source synthesis, yet their evaluation remains challenging. Existing benchmarks often require annotation-intensive task construction, rely on static…
In numerous artificial intelligence applications, the collaborative efforts of multiple intelligent agents are imperative for the successful attainment of target objectives. To enhance coordination among these agents, a distributed…
Accurate trajectory prediction is crucial for ensuring safe and efficient autonomous driving. However, most existing methods overlook complex interactions between traffic participants that often govern their future trajectories. In this…
Developing safe human-robot interaction systems is a necessary step towards the widespread integration of autonomous agents in society. A key component of such systems is the ability to reason about the many potential futures (e.g.…
Web agents based on large language models have demonstrated promising capability in automating web tasks. However, current web agents struggle to reason out sensible actions due to the limitations of predicting environment changes, and…
A lot of scientific works are published in different areas of science, technology, engineering and mathematics. It is not easy, even for experts, to judge the quality of authors, papers and venues (conferences and journals). An objective…
In numerous artificial intelligence applications, the collaborative efforts of multiple intelligent agents are imperative for the successful attainment of target objectives. To enhance coordination among these agents, a distributed…
Agent frameworks increasingly encode tool-using behavior as explicit workflow graphs, yet safety enforcement remains a runtime concern. These frameworks expose analyzable graph structure through their APIs, enabling pre-deployment static…
In this paper we tackle the problem of routing multiple agents in a coordinated manner. This is a complex problem that has a wide range of applications in fleet management to achieve a common goal, such as mapping from a swarm of robots and…
Real-world autonomous planning requires coordinating tightly coupled constraints where a single decision dictates the feasibility of all subsequent actions. However, existing benchmarks predominantly feature loosely coupled constraints…