Beyond Clicks: Building a More Programmable Web
Researchers propose a new layer of typed functions, dubbed ‘web verbs’, to enable more reliable and efficient interactions between web agents and online services.
Science
The Echo Chamber Effect in Conversational AI Evaluation
New research reveals that human ratings of conversational recommender systems are surprisingly susceptible to bias, casting doubt on their use as reliable benchmarks.
Mapping the Future with AI Agents
A new framework combines the power of artificial intelligence with geospatial tools to unlock deeper insights from Earth observation data.
Slithering Towards Efficiency: How Surfaces Power Animal Movement and Fluid Flow
![Locomotion and fluid pumping across diverse biological systems-from freshwater snails exhibiting undulatory movement near surfaces where velocity scales with wave amplitude [latex]\frac{V}{V\_{wave}}\sim\frac{3}{2}\left(\frac{a}{h\_{0}}\right)^{2}[/latex], to aerial fliers like bats and bees generating lift or vortex streets-share a common geometric scaling principle relating flow velocity to the ratios of chord length, amplitude, and characteristic height [latex]C\_{L0}^{squeeze}\sim\frac{c}{a}\frac{c}{h\_{0}}[/latex] and [latex]\frac{V\_{vortex}}{V\_{flap}}\sim\frac{c}{a}\frac{c}{h\_{0}}[/latex], suggesting a unified physics governing efficient movement and fluid manipulation in confined spaces.](https://arxiv.org/html/2602.16978v1/x1.png)
A new review unifies the physics behind locomotion and fluid transport near surfaces, revealing how animals and engineered systems exploit ground effects for enhanced performance.
Charting Age: A New Knowledge System for Forensic Dentistry
![The system models the essential entities within judicial and forensic age assessment, encompassing data from legal dental and medical examinations performed on undocumented individuals-detailed as [latex]Legal\,Dental\,Medical\,Exam\,Data[/latex]-and culminating in a comprehensive [latex]Report\,Data[/latex] that formally concludes the age determination process, with relationships defined through [latex]rdfs:subClassOf[/latex] and specific object properties.](https://arxiv.org/html/2602.16714v1/img/main_annotated.png)
Researchers have developed a comprehensive framework to standardize and improve the accuracy of dental age estimation, a critical process in forensic investigations.
Charming Bots, Shady Influence: How AI Personalities Sway Our Choices
New research reveals how the carefully crafted personalities of conversational AI agents can subtly influence user perceptions and even drive behavioral changes, like charitable giving.
Decoding the Digital Classroom: How Students Interact with AI Cybersecurity Tutors
A new study examines real-world student interactions with AI-powered teaching assistants in a cybersecurity course, revealing key insights into learning patterns and tutor effectiveness.
When Code Agents Stumble: A New Approach to Reliable AI Software Development
A comprehensive study reveals common failure patterns in AI-powered coding agents and introduces a self-correcting system to dramatically improve their performance.
Who Teaches the Machines?
As AI systems increasingly shape what we know, it’s crucial to consider how their knowledge is governed and who holds the authority over it.
Orchestrating AI: How Dynamic Teamwork Boosts Code Creation
![AgentConductor addresses complex code problems through a three-stage process: initial supervised fine-tuning [latex]SFT[/latex] on varied network topologies instills structural understanding in the base [latex]Qwen-2.5-Instruct-3B[/latex] language model, followed by reinforcement learning with [latex]GRPO[/latex] to create a task-specific orchestrator capable of adapting network difficulty, and culminating in dynamic, multi-turn topology generation for end-to-end problem solving.](https://arxiv.org/html/2602.17100v1/x3.png)
A new system intelligently designs how multiple AI agents collaborate to generate code, achieving better results with fewer resources.