Science – Page 123

Building Smarter AI Agents: A System for Adaptive Configuration

14.02.2026 by ebaster

The method navigates a vast configuration space-spanning thousands of possibilities-to optimize performance for the Qwen 2.5 7B Instruct model across multiple datasets, demonstrating a capacity to adapt and improve beyond baseline results.

New research details a framework for automatically optimizing the workflows and instructions of AI agents powered by large language models.

The AI Negotiation Edge: Control vs. Collective Gain

14.02.2026 by ebaster

Delegate agents demonstrably improve trade outcomes by consistently proposing offers that yield a significant increase in receiver surplus-a statistically significant shift not observed in non-AI-assisted scenarios [latex] (p<0.01) [/latex], suggesting a capacity for mutually beneficial negotiation.

New research explores how different levels of AI involvement in multi-party bargaining – from advice to full delegation – impacts strategic choices and overall outcomes.

Bridging the AI Gap for Language Professionals

14.02.2026 by ebaster

Jupyter notebooks facilitate the didactic exploration of complex neural network processes, as demonstrated by the visualization of both embedding transformations within hidden layers and the detailed examination of self-attention mechanisms in transformer language models.

A new technical curriculum aims to equip translators and communicators with the skills needed to navigate the rapidly evolving landscape of language-oriented artificial intelligence.

Robots Learn by Building Their Own Worlds

14.02.2026 by ebaster

Complex long-horizon tasks are systematically decomposed into interconnected simple tasks, establishing a framework where inter-task edges facilitate transitions between distinct object manipulations or resets of temporal states, thereby enabling solutions to problems requiring extended sequential reasoning.

Researchers have developed a system that allows robots to generate increasingly complex environments and tasks, enabling more robust learning for long-horizon challenges.

The Kitsch Machine: When AI Art Goes Wrong

14.02.2026 by ebaster

Generative AI is flooding the art world with images, but a critical look reveals a troubling tendency towards superficiality and the normalization of kitsch.

Robots Learn Spatial Reasoning from Diffusion Models

14.02.2026 by ebaster

Researchers have developed a new framework that imbues robots with improved geometric understanding by distilling knowledge from powerful diffusion models.

Reasoning with Agents: A New Logic for Smarter Systems

14.02.2026 by ebaster

Researchers are blending the power of symbolic reasoning with neural networks to create multi-agent systems that can better understand, diagnose, and coordinate with each other.

Seeing the World Through WiFi: AM-FM Ushers in a New Era of Ambient Intelligence

14.02.2026 by ebaster

The AM-FM framework leverages continuous channel state information from distributed IoT devices to enable self-supervised pre-training, employing contrastive learning, masked reconstruction, and physics-informed autocorrelation function prediction, ultimately facilitating parameter-efficient adaptation to downstream tasks through lightweight temporal classifiers or bottleneck adapters.

Researchers have developed a foundation model that leverages readily available WiFi signals to understand and interpret surrounding environments, paving the way for smarter, more responsive ambient systems.

Robots Learn to Plan Ahead with a New World Model

14.02.2026 by ebaster

Researchers have developed a hierarchical system that allows robots to better understand and predict the outcomes of complex actions, significantly improving long-term task planning.

Bridging the Gap Between AI and Physics in Fluid Dynamics

14.02.2026 by ebaster

Researchers have developed a novel framework that combines neural reasoning with deterministic validation to create more accurate and reliable autonomous simulations of complex fluid flows.