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.
A comprehensive study reveals common failure patterns in AI-powered coding agents and introduces a self-correcting system to dramatically improve their performance.
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.
![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.
A new framework combines the creative power of neural networks with the rigor of formal logic to generate complex molecules that meet precise chemical and functional requirements.
A new algorithm allows groups of autonomous agents to seamlessly switch between leading and herding behaviors for more efficient collective transport.
New research suggests humans are surprisingly willing to perceive empathy in advice generated by artificial intelligence systems.
![The study demonstrates a consistent reduction in token usage-averaging 28,500 tokens per step-across ten agent iterations, initially achieving 95% savings which gradually decreased to 57% as contextual history accumulated, indicating a predictable relationship between information retention and computational cost represented by [latex] \Delta Tokens = f(History) [/latex].](https://arxiv.org/html/2602.17046v1/results/agent_loops_comprehensive.png)
A new approach dynamically selects the most relevant instructions and tools for AI agents, reducing computational costs and improving performance.
![The analysis of an [latex]Al_{70}Co_{10}Fe_5Ni_{10}Cu_5[/latex] decagonal quasicrystalline alloy reveals a layer-dependent structure, where atomic composition, electronegativity, valence electron concentration, and coordination number vary systematically across six topologically defined layers, indicating a gradient in chemical and electronic properties throughout the nanoparticle.](https://arxiv.org/html/2602.17528v1/x1.png)
A new framework efficiently assesses the stability of complex nanoparticles, minimizing the need for extensive computational simulations.
A new motion planning framework leverages formal logic and advanced robustness metrics to enable robots to reliably execute complex tasks.