Research

Agent Skill Framework: Perspectives on the Potential of Small Language Models in Industrial Environments

• Computer Science > Artificial Intelligence [Submitted on 18 Feb 2026] Title:Agent Skill Framework: Perspectives on the Potential of Small Language Models in Industrial Environmen

Causally-Guided Automated Feature Engineering with Multi-Agent Reinforcement Learning

• Computer Science > Artificial Intelligence [Submitted on 18 Feb 2026] Title:Causally-Guided Automated Feature Engineering with Multi-Agent Reinforcement Learning View PDF HTML (e

Creating a digital poet

• Computer Science > Artificial Intelligence [Submitted on 18 Feb 2026] Title:Creating a digital poet View PDF HTML (experimental)Abstract:Can a machine write good poetry? • Any po

EdgeNav-QE: QLoRA Quantization and Dynamic Early Exit for LAM-based Navigation on Edge Devices

• Computer Science > Robotics [Submitted on 12 Jan 2026] Title:EdgeNav-QE: QLoRA Quantization and Dynamic Early Exit for LAM-based Navigation on Edge Devices View PDF HTML (experim

EnterpriseGym Corecraft: Training Generalizable Agents on High-Fidelity RL Environments

• Computer Science > Artificial Intelligence [Submitted on 18 Feb 2026] Title:EnterpriseGym Corecraft: Training Generalizable Agents on High-Fidelity RL Environments View PDF HTML

Evidence-Grounded Subspecialty Reasoning: Evaluating a Curated Clinical Intelligence Layer on the 2025 Endocrinology Board-Style Examination

• Computer Science > Artificial Intelligence [Submitted on 17 Feb 2026] Title:Evidence-Grounded Subspecialty Reasoning: Evaluating a Curated Clinical Intelligence Layer on the 2025

Framework of Thoughts: A Foundation Framework for Dynamic and Optimized Reasoning based on Chains, Trees, and Graphs

• Computer Science > Artificial Intelligence [Submitted on 18 Feb 2026] Title:Framework of Thoughts: A Foundation Framework for Dynamic and Optimized Reasoning based on Chains, Tre

GPSBench: Do Large Language Models Understand GPS Coordinates?

• Computer Science > Artificial Intelligence [Submitted on 18 Feb 2026] Title:GPSBench: Do Large Language Models Understand GPS Coordinates? • View PDF HTML (experimental)Abstract:

How Uncertain Is the Grade? A Benchmark of Uncertainty Metrics for LLM-Based Automatic Assessment

• Computer Science > Artificial Intelligence [Submitted on 17 Feb 2026] Title:How Uncertain Is the Grade? • A Benchmark of Uncertainty Metrics for LLM-Based Automatic Assessment Vi

Improving Interactive In-Context Learning from Natural Language Feedback

• Computer Science > Artificial Intelligence [Submitted on 17 Feb 2026] Title:Improving Interactive In-Context Learning from Natural Language Feedback View PDF HTML (experimental)A

Learning Personalized Agents from Human Feedback

• Computer Science > Artificial Intelligence [Submitted on 18 Feb 2026] Title:Learning Personalized Agents from Human Feedback View PDF HTML (experimental)Abstract:Modern AI agents

Leveraging Large Language Models for Causal Discovery: a Constraint-based, Argumentation-driven Approach

• Computer Science > Artificial Intelligence [Submitted on 18 Feb 2026] Title:Leveraging Large Language Models for Causal Discovery: a Constraint-based, Argumentation-driven Approa

Multi-agent cooperation through in-context co-player inference

• Computer Science > Artificial Intelligence [Submitted on 18 Feb 2026] Title:Multi-agent cooperation through in-context co-player inference View PDF HTML (experimental)Abstract:Ac

Optimization Instability in Autonomous Agentic Workflows for Clinical Symptom Detection

• Computer Science > Artificial Intelligence [Submitted on 17 Feb 2026] Title:Optimization Instability in Autonomous Agentic Workflows for Clinical Symptom Detection View PDF HTML

Revolutionizing Long-Term Memory in AI: New Horizons with High-Capacity and High-Speed Storage

• Computer Science > Artificial Intelligence [Submitted on 18 Feb 2026] Title:Revolutionizing Long-Term Memory in AI: New Horizons with High-Capacity and High-Speed Storage View PD

Toward Scalable Verifiable Reward: Proxy State-Based Evaluation for Multi-turn Tool-Calling LLM Agents

• Computer Science > Artificial Intelligence [Submitted on 18 Feb 2026] Title:Toward Scalable Verifiable Reward: Proxy State-Based Evaluation for Multi-turn Tool-Calling LLM Agents

Towards a Science of AI Agent Reliability

• Computer Science > Artificial Intelligence [Submitted on 18 Feb 2026] Title:Towards a Science of AI Agent Reliability View PDF HTML (experimental)Abstract:AI agents are increasin

Towards Efficient Constraint Handling in Neural Solvers for Routing Problems

• Computer Science > Artificial Intelligence [Submitted on 17 Feb 2026] Title:Towards Efficient Constraint Handling in Neural Solvers for Routing Problems View PDF HTML (experiment

Verifiable Semantics for Agent-to-Agent Communication

• Computer Science > Artificial Intelligence [Submitted on 18 Feb 2026] Title:Verifiable Semantics for Agent-to-Agent Communication View PDF HTML (experimental)Abstract:Multiagent

What Persona Are We Missing? Identifying Unknown Relevant Personas for Faithful User Simulation

• Computer Science > Human-Computer Interaction [Submitted on 3 Jan 2026] Title:What Persona Are We Missing? • Identifying Unknown Relevant Personas for Faithful User Simulation Vi

Identifying spatial single-cell-level interactions with graph transformer

• Subjects Cellular signalling networks Multicellular systems Identifying cell-cell interactions from imaging-based spatial transcriptomics suffers from limited gene panels. • A ne

Attributing and situating knowledge cannot be left to language models

• Subjects Authorship Ethics Meticulous citation is a marker of well-researched, serious scholarship. • Citations do a lot more than attributing credit; they situate claims within

A federated graph learning method to realize multi-party collaboration for molecular discovery

• Abstract Optimizing molecular resource utilization for molecular discovery requires collaborative efforts across research institutions and organizations to accelerate progress. •

What matters in building vision-language-action models for generalist robots

• Nature Machine Intelligence, Published online: 11 February 2026; doi:10.1038/s42256-025-01168-7 Vision-language-action models recently emerged as a tool for robotics. • Here Li a

When large language models are reliable for judging empathic communication

• Nature Machine Intelligence, Published online: 11 February 2026; doi:10.1038/s42256-025-01169-6 Kumar et al. • show that large language models (LLMs) nearly match expert reliabil

Reusability Report: Evaluating the performance of a meta-learning foundation model on predicting the antibacterial activity of natural products

• Nature Machine Intelligence, Published online: 12 February 2026; doi:10.1038/s42256-026-01187-y This Reusability Report tests the ability of a foundation model, ActFound, to pred

A flaw in using pretrained protein language models in protein-protein interaction inference models

• Nature Machine Intelligence, Published online: 13 February 2026; doi:10.1038/s42256-025-01176-7 The usage of pretrained protein language models (pLMs) is rapidly growing. • Howev

Parallel hierarchical encoding of linguistic representations in the human auditory cortex and recurrent automatic speech recognition systems

• Nature Machine Intelligence, Published online: 17 February 2026; doi:10.1038/s42256-026-01185-0 Keshishian, Mischler et al. • report that a recurrent automatic speech recognition

Grasshopper-inspired wing design improves gliding performance

• Science Robotics, Volume 11, Issue 111, February 2026.

Low-voltage and high-output dielectric elastomer actuators for untethered soft machines working at 200 volts

• Science Robotics, Volume 11, Issue 111, February 2026.

The codevelopment of soft robotics and assistive technology

• Science Robotics, Volume 11, Issue 111, February 2026.

Five Berkeley Lab Scientists Receive DOE Early Career Research Awards

• Five Berkeley Lab Scientists Receive DOE Early Career Research Awards Article Emerging Ideas Five scientists from Lawrence Berkeley National Laboratory (Berkeley Lab) have receiv

AgriWorld:A World Tools Protocol Framework for Verifiable Agricultural Reasoning with Code-Executing LLM Agents

• Computer Science > Artificial Intelligence [Submitted on 17 Feb 2026] Title:AgriWorld:A World Tools Protocol Framework for Verifiable Agricultural Reasoning with Code-Executing L

Attention-gated U-Net model for semantic segmentation of brain tumors and feature extraction for survival prognosis

• Computer Science > Artificial Intelligence [Submitted on 14 Feb 2026] Title:Attention-gated U-Net model for semantic segmentation of brain tumors and feature extraction for survi

Common Belief Revisited

• Computer Science > Artificial Intelligence [Submitted on 17 Feb 2026] Title:Common Belief Revisited View PDF HTML (experimental)Abstract:Contrary to common belief, common belief

da Costa and Tarski meet Goguen and Carnap: a novel approach for ontological heterogeneity based on consequence systems

• Computer Science > Artificial Intelligence [Submitted on 16 Feb 2026] Title:da Costa and Tarski meet Goguen and Carnap: a novel approach for ontological heterogeneity based on co

EAA: Automating materials characterization with vision language model agents

• Computer Science > Artificial Intelligence [Submitted on 17 Feb 2026] Title:EAA: Automating materials characterization with vision language model agents View PDF HTML (experiment

Enhancing Diversity and Feasibility: Joint Population Synthesis from Multi-source Data Using Generative Models

• Computer Science > Artificial Intelligence [Submitted on 17 Feb 2026] Title:Enhancing Diversity and Feasibility: Joint Population Synthesis from Multi-source Data Using Generativ

GenAI-LA: Generative AI and Learning Analytics Workshop (LAK 2026), April 27--May 1, 2026, Bergen, Norway

• Computer Science > Artificial Intelligence [Submitted on 17 Feb 2026] Title:GenAI-LA: Generative AI and Learning Analytics Workshop (LAK 2026), April 27–May 1, 2026, Bergen, Nor

Improving LLM Reliability through Hybrid Abstention and Adaptive Detection

• Computer Science > Artificial Intelligence [Submitted on 17 Feb 2026] Title:Improving LLM Reliability through Hybrid Abstention and Adaptive Detection View PDF HTML (experimental

Mind the (DH) Gap! A Contrast in Risky Choices Between Reasoning and Conversational LLMs

• Computer Science > Artificial Intelligence [Submitted on 16 Feb 2026] Title:Mind the (DH) Gap! • A Contrast in Risky Choices Between Reasoning and Conversational LLMs View PDF HT

Panini: Continual Learning in Token Space via Structured Memory

• Computer Science > Artificial Intelligence [Submitted on 16 Feb 2026] Title:Panini: Continual Learning in Token Space via Structured Memory View PDF HTML (experimental)Abstract:L

Predicting Invoice Dilution in Supply Chain Finance with Leakage Free Two Stage XGBoost, KAN (Kolmogorov Arnold Networks), and Ensemble Models

• Computer Science > Artificial Intelligence [Submitted on 16 Feb 2026] Title:Predicting Invoice Dilution in Supply Chain Finance with Leakage Free Two Stage XGBoost, KAN (Kolmogor

Protecting Language Models Against Unauthorized Distillation through Trace Rewriting

• Computer Science > Artificial Intelligence [Submitted on 16 Feb 2026] Title:Protecting Language Models Against Unauthorized Distillation through Trace Rewriting View PDF HTML (ex

Quantifying construct validity in large language model evaluations

• Computer Science > Artificial Intelligence [Submitted on 17 Feb 2026] Title:Quantifying construct validity in large language model evaluations View PDF HTML (experimental)Abstrac

ResearchGym: Evaluating Language Model Agents on Real-World AI Research

• Computer Science > Artificial Intelligence [Submitted on 16 Feb 2026] Title:ResearchGym: Evaluating Language Model Agents on Real-World AI Research View PDF HTML (experimental)Ab

Secure and Energy-Efficient Wireless Agentic AI Networks

• Computer Science > Artificial Intelligence [Submitted on 16 Feb 2026] Title:Secure and Energy-Efficient Wireless Agentic AI Networks View PDF HTML (experimental)Abstract:In this

When Remembering and Planning are Worth it: Navigating under Change

• Computer Science > Artificial Intelligence [Submitted on 17 Feb 2026] Title:When Remembering and Planning are Worth it: Navigating under Change View PDF HTML (experimental)Abstra

World-Model-Augmented Web Agents with Action Correction

• Computer Science > Artificial Intelligence [Submitted on 17 Feb 2026] Title:World-Model-Augmented Web Agents with Action Correction View PDF HTML (experimental)Abstract:Web agent

Bioinspired adaptive pupil reflex based on liquid-metal shape-shifters for machine vision

• Science Robotics, Volume 11, Issue 111, February 2026.

Scalable robot collective resilience by sharing resources

• Science Robotics, Volume 11, Issue 111, February 2026.

Science on the Double: How an AI-Powered 'Digital Twin' Accelerates Chemistry and Materials Discoveries

• The post Science on the Double: How an AI-Powered ‘Digital Twin’ Accelerates Chemistry and Materials Discoveries appeared first on Berkeley Lab News Center . • The post What Is a

What Is a Digital Twin?

• What Is a Digital Twin? • Video AI Digital twins are transforming how scientists study and improve complex systems - reducing the time between discovery and delivery. • Learn wha

Authorization of prognostic AI medical devices

• Subjects Health policy Medical humanities Less than 2% of artificial intelligence devices authorized by the US Food and Drug Agency are prognostic, with prediction horizons rangi

A Geometric Taxonomy of Hallucinations in LLMs

• Computer Science > Artificial Intelligence [Submitted on 26 Jan 2026] Title:A Geometric Taxonomy of Hallucinations in LLMs View PDF HTML (experimental)Abstract:The term ‘hallucin

Agentic AI for Commercial Insurance Underwriting with Adversarial Self-Critique

• Computer Science > Artificial Intelligence [Submitted on 21 Jan 2026] Title:Agentic AI for Commercial Insurance Underwriting with Adversarial Self-Critique View PDF HTML (experim

AST-PAC: AST-guided Membership Inference for Code

• Computer Science > Artificial Intelligence [Submitted on 30 Jan 2026] Title:AST-PAC: AST-guided Membership Inference for Code View PDF HTML (experimental)Abstract:Code Large Lang

BotzoneBench: Scalable LLM Evaluation via Graded AI Anchors

• Computer Science > Artificial Intelligence [Submitted on 22 Jan 2026] Title:BotzoneBench: Scalable LLM Evaluation via Graded AI Anchors View PDF HTML (experimental)Abstract:Large

DPBench: Large Language Models Struggle with Simultaneous Coordination

• Computer Science > Artificial Intelligence [Submitted on 2 Feb 2026] Title:DPBench: Large Language Models Struggle with Simultaneous Coordination View PDF HTML (experimental)Abst

General learned delegation by clones

• Computer Science > Artificial Intelligence [Submitted on 3 Feb 2026] Title:General learned delegation by clones View PDF HTML (experimental)Abstract:Frontier language models impr