AI

Clarifai deletes 3 million photos that OkCupid provided to train facial recognition AI, report says

ReasoningBank: Enabling agents to learn from experience

Top 10 Free AI Stock Trading Bots in 2026 for Beginners: Passive Income Guide

The article highlights the growing adoption of AI-powered trading bots among beginner investors in 2026, positioning automated systems as alternatives to manual stock market analysis. These bots aim to eliminate emotional decision-making and provide passive income opportunities through algorithmic trading strategies.

Agentic Frameworks for Reasoning Tasks: An Empirical Study

Agentic Risk-Aware Set-Based Engineering Design

RankGuide: Tensor-Rank-Guided Routing and Steering for Efficient Reasoning

Evaluating Tool-Using Language Agents: Judge Reliability, Propagation Cascades, and Runtime Mitigation in AgentProp-Bench

Debate as Reward: A Multi-Agent Reward System for Scientific Ideation via RL Post-Training

When Agents Go Quiet: Output Generation Capacity and Format-Cost Separation for LLM Document Synthesis

CT Open: An Open-Access, Uncontaminated, Live Platform for the Open Challenge of Clinical Trial Outcome Prediction

Don't Start What You Can't Finish: A Counterfactual Audit of Support-State Triage in LLM Agents

Know When to Trust the Skill: Delayed Appraisal and Epistemic Vigilance for Single-Agent LLMs

Machine individuality: Separating genuine idiosyncrasy from response bias in large language models

PersonalHomeBench: Evaluating Agents in Personalized Smart Homes

GRAIL: Autonomous Concept Grounding for Neuro-Symbolic Reinforcement Learning

Step-GRPO: Internalizing Dynamic Early Exit for Efficient Reasoning

Beyond Text-Dominance: Understanding Modality Preference of Omni-modal Large Language Models

The Cognitive Penalty: Ablating System 1 and System 2 Reasoning in Edge-Native SLMs for Decentralized Consensus

ClimAgent: LLM as Agents for Autonomous Open-ended Climate Science Analysis

Alignment Imprint: Zero-Shot AI-Generated Text Detection via Provable Preference Discrepancy

Playing Psychic: Using Thought Trees to Predict Reasoning Models Accuracy on Coding Tasks

LLMs can persuade only psychologically susceptible humans on societal issues, via trust in AI and emotional appeals, amid logical fallacies

MCPO: Mastery-Consolidated Policy Optimization for Large Reasoning Models

Rule-VLN: Bridging Perception and Compliance via Semantic Reasoning and Geometric Rectification

Mini-BEHAVIOR-Gran: Revealing U-Shaped Effects of Instruction Granularity on Language-Guided Embodied Agents