Related papers: CodeCompass: Navigating the Navigation Paradox in …

Real-world requests to AI agents are fundamentally underspecified. Natural human communication relies on shared context and unstated constraints that speakers expect listeners to infer. Current agentic benchmarks test explicit…

Every document format in existence was designed for a human reader moving linearly through text. Autonomous LLM agents do not read - they retrieve. This fundamental mismatch forces agents to inject entire documents into their context…

Recent advances in agentic frameworks have enabled AI agents to perform complex reasoning and decision-making. However, evidence comparing their reasoning performance, efficiency, and practical suitability remains limited. To address this…

With the rapid advancement of tool-use capabilities in Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) is shifting from static, one-shot retrieval toward autonomous, multi-turn evidence acquisition. However, existing…

With AI agents increasingly deployed as long-running systems, it becomes essential to autonomously construct and continuously evolve customized software to enable interaction within dynamic environments. Yet, existing benchmarks evaluate…

Modern LLM agents increasingly rely on reusable skills, and as they interact with personal applications, web browsers, and other interfaces, skill libraries can scale to thousands of skills. Scaling to larger skill sets introduces two key…

Active learning selects informative samples for annotation within budget, which has proven efficient recently on object detection. However, the widely used active detection benchmarks conduct image-level evaluation, which is unrealistic in…

Understanding and following natural language instructions while navigating through complex, real-world environments poses a significant challenge for general-purpose robots. These environments often include obstacles and pedestrians, making…

We investigate the task of object goal navigation in unknown environments where the target is specified by a semantic label (e.g. find a couch). Such a navigation task is especially challenging as it requires understanding of semantic…

In Multiagent Path Finding (MAPF), the goal is to compute efficient, collision-free paths for multiple agents navigating a network from their sources to targets, minimizing the schedule's makespan-the total time until all agents reach their…

Repository aware coding agents often struggle to recover build and test structure, especially in multilingual projects where cross language dependencies are encoded across heterogeneous build systems and tooling. We introduce the Repository…

Modern web test suites rot. A UI refactor breaks locators, a timing change causes race conditions, and within weeks developers abandon the suite entirely. This paper presents an AI-driven autonomous testing framework that addresses these…

Web browsers are a portal to the internet, where much of human activity is undertaken. Thus, there has been significant research work in AI agents that interact with the internet through web browsing. However, there is also another…

Navigation in cluttered underwater environments is challenging, especially when there are constraints on communication and self-localisation. Part of the fully distributed underwater navigation problem has been resolved by introducing…

We introduce CRAFT, a multi-agent benchmark for evaluating pragmatic communication in large language models under strict partial information. In this setting, multiple agents with complementary but incomplete views must coordinate through…

Conversational agents are increasingly deployed in knowledge-intensive settings, where correct behavior depends on retrieving and applying domain-specific knowledge from large, proprietary, and unstructured corpora during live interactions…

Enterprise API design is often bottlenecked by the tension between rapid feature delivery and the rigorous maintenance of usability standards. We present an industrial case study evaluating an AI-assisted design workflow trained on API…

Cooperative multi-agent reinforcement learning agents that act on partial local observations face a fundamental information bottleneck: the knowledge needed to select jointly optimal actions is scattered across the team, yet each agent must…

Cyber threat intelligence (CTI) analysts must answer complex questions over large collections of narrative security reports. Retrieval-augmented generation (RAG) systems help language models access external knowledge, but traditional vector…

Object Navigation (ObjectNav) has made great progress with large language models (LLMs), but still faces challenges in memory management, especially in long-horizon tasks and dynamic scenes. To address this, we propose TopoNav, a new…