Prépublication
· 2026 arXiv
EN
3D object composition is pivotal to digital content creation and robot simulation, while also serving as a critical testbed for physical intelligence in foundation models. Previous methods either leverage large language models to directly predict object coordi...
Weichen Lyu, Chong Xia et al.
#cs.AI
Prépublication
· 2026 arXiv
EN
Reusable skills let LLM agents load task-specific instructions on demand, but they make execution depend on implicit routing over skill metadata. We test whether this design scales by holding SkillsBench tasks and their golden skills fixed while adding irrelev...
Jinlin Liu, Wei Chen et al.
#cs.AI
Prépublication
· 2026 arXiv
EN
Buildings cause nearly 40\% of carbon emissions in the US. Of total building emissions, HVAC systems are responsible for approximately 40-60\% and account for 15\% of global energy consumption. Despite advances in artificial intelligence, most buildings still...
Judah Goldfeder, Ayush Rai et al.
#cs.AI
Prépublication
· 2026 arXiv
EN
Tool-call judges evaluate argument values proposed by LLM agents. We find that they accept a correct value less often when their input holds no reference for it, that is, no text that says what the value should be. This happens when the value is a default valu...
Linhai Ma, Yan Wang et al.
#cs.AI
Prépublication
· 2026 arXiv
EN
Terminal agents have shown strong abilities in complex coding tasks. However, they often struggle to recover from errors during long-running execution (e.g., command errors, faulty implementations), eventually leading to task failures. To this end, we present...
Wei Xie, Kaituo Feng et al.
#cs.AI
Prépublication
· 2026 arXiv
EN
Language models increasingly support or automate information retrieval from document collections too large to index. This task is difficult when it requires specialist linguistic or scientific knowledge. We used the Wikipedia Game to test language models on an...
Alexander Hickey, Joanna Knight et al.
#cs.AI
Prépublication
· 2026 arXiv
EN
As AI agents increasingly rely on external tools, accurate retrieval is essential for reliable behavior. Existing methods optimize semantic relevance but largely ignore tool availability during execution. To address this gap, we propose RATED (Reliability-Awar...
Weiliang Chen, Song Liao
#cs.AI
Prépublication
· 2026 arXiv
EN
Personal agents increasingly connect to services across the web and applications by using tools. As the effects of their actions accumulate and interact across services, unintended or harmful outcomes can arise when agents fulfill benign user requests. Proacti...
Yeonsung Jung, Zhiyuan Wang et al.
#cs.AI
Prépublication
· 2026 arXiv
EN
Comics are one of the great visual records of the twentieth century: hundreds of thousands of pages in which a mass readership saw its leaders, its wars and its heroes. Most of this record has never been studied as a whole; comics scholarship proceeds one book...
Emilio Ferrara
#cs.AI
Prépublication
· 2026 arXiv
EN
We propose BrickBench, a benchmark for agentic text-conditioned LEGO-set design. Given a prompt, an agent is tasked with producing an assembly that not only satisfies semantic and design criteria, but that can also be physically built. To do so, it must select...
Peter Kulits, Yiqing Xu et al.
#cs.AI
Prépublication
· 2026 arXiv
EN
AI agents can now conduct real-world cyberattacks, scale up capabilities with the number of agents, and collectively pursue misaligned goals to obtain rewards. Together, these factors raise the risk of a population explosion of misaligned agents: agents could...
Erin Crawley, Hidenori Tanaka
#cs.AI
Prépublication
· 2026 arXiv
EN
Safety benchmarks typically report one overall score for a suite of datasets, each of which may target one or more safety-related attributes, so models with similar overall scores can have very different attribute profiles. Comparing models is more tractable a...
Christopher M. Stewart, Preston Botter et al.
#cs.AI