Building with Logic: AI Designs Molecules to Specification
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.
Science
The Art of the Collective: Balancing Leadership and Following
A new algorithm allows groups of autonomous agents to seamlessly switch between leading and herding behaviors for more efficient collective transport.
Can AI Really Understand How We Feel?
New research suggests humans are surprisingly willing to perceive empathy in advice generated by artificial intelligence systems.
Give Agents a Smarter Toolkit: Dynamic Instructions for Cost-Effective AI
![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.
Predicting Nanoparticle Stability with Machine Learning
![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.
Robotics Gets Smarter: Planning with Logic and Robustness
A new motion planning framework leverages formal logic and advanced robustness metrics to enable robots to reliably execute complex tasks.
Smarter Grading: How AI is Boosting Student Writing
![When teaching assistants are empowered to readily adopt and refine suggestions generated by an AI feedback system-FeedbackWriter-student revisions demonstrate a quality increase equivalent to moving a student from the 50th to the 70th percentile, attributable to the AI’s capacity to deliver actionable feedback that fosters independent learning-a benefit exceeding that of solely human-provided feedback [latex] (Cohen’s\ d = 0.50) [/latex].](https://arxiv.org/html/2602.16820v1/img/teaser3.png)
New research reveals that pairing teaching assistants with AI feedback tools significantly improves the quality of revisions students make to their work.
Beyond Rules: Ethical Systems That Adapt
As systems become increasingly autonomous, static ethical guidelines are proving insufficient, demanding a new approach to runtime ethics and value alignment.
Beyond Hypergraphs: Rethinking Complex Network Interactions
New research challenges the notion that hypergraphs offer a fundamentally richer framework for modeling complex systems than standard graphs.
The Art of Persuasion: Can AI Talk Its Way to Success?
New research reveals that large language models can effectively persuade people despite lacking a crucial human ability: understanding what others are thinking.