Research

142 articles

Research
The promise and peril of using visual AI to study cities MIT News - Artificial intelligence · 1h ago
Research
Silent Failures in Agent-Tool Interaction: An Audit of ToolUniverse cs.AI updates on arXiv.org · 1h ago
Research
Harness as a Language: A Minimalist Agent Framework With Maximal Expressivity cs.AI updates on arXiv.org · 1h ago
Research
TwinCheck: Evidence-Grounded Negative-Twin Verification for Stateful Tool Agents cs.AI updates on arXiv.org · 1h ago
Research
Building Socio-Affective Artificial Intelligence for Interactive Multi-Agent Simulations cs.AI updates on arXiv.org · 1h ago
Research
Which Objectives Need a Dial? Predicting Objective Conflict and Covering Trade-offs in Steerable Pluralistic Alignment cs.AI updates on arXiv.org · 1h ago
Research
Escaping Python Dependency Hell: A Hybrid Replay-and-Repair Pipeline for Python Dependency Resolution cs.AI updates on arXiv.org · 1h ago
Research
Same evidence, different judgments: Evidence noncommutative in vision/speech-text conflicts cs.AI updates on arXiv.org · 1h ago
Research
Reinforcement Learning with Decomposed Subtasks cs.AI updates on arXiv.org · 1h ago
Research
Training Intelligent Voice Assistant Wakeup with Controllable Synthetic Conversations cs.AI updates on arXiv.org · 1h ago
Research
Are Stated Reasoning Steps Causally Load-Bearing? cs.AI updates on arXiv.org · 1h ago
Research
Math Reasoning in LLMs is Organized by Approach, Not Topic cs.AI updates on arXiv.org · 1h ago
Research
Propose, Don't Judge: An Anytime-Valid Referee for LLM Agents That Mine Investment Factors cs.AI updates on arXiv.org · 1h ago
Research
Policy-as-Skill: Governed LLM Decision Support with Evidence, Deterministic Control, and Audit cs.AI updates on arXiv.org · 1h ago
Research
Provably Complete Generalized Planning with LLMs cs.AI updates on arXiv.org · 1h ago
Research
Do We Need Complex Topology Control? Distinct-Peer Random Routing Improves Cost-Efficiency in Sparse Multi-Agent Debate cs.AI updates on arXiv.org · 1h ago
Research
Enhancing Small Language Models for Power Outage Report Generation via Minimum Risk Training cs.AI updates on arXiv.org · 1h ago
Research
XLOG: A CUDA-Native Engine for Neurosymbolic Integration cs.AI updates on arXiv.org · 1h ago
Research
CAVEAT: Towards Robust Computer-Use Agents in Incentive-Misaligned Environments cs.AI updates on arXiv.org · 1h ago
Research
DRSR: Learning Set-Level Deletion Risk for Efficient Long-Horizon Agents cs.AI updates on arXiv.org · 1h ago
Research
TimeEvo: Failure-Driven Self-Evolution of a Time Series Agent cs.AI updates on arXiv.org · 1h ago
Research
Offloaded inference for real-world physical AI robotics Microsoft Research · 13h ago
Research
I Trained a Tiny Network to Compress Data. It Drew a Pentagon. Towards Data Science · 14h ago
Research
MIT welcomes David Siegel SM ’86, PhD ’91 as its next Innovation Fellow MIT News - Artificial intelligence · 14h ago
Research
From Words to Vectors: What Happens in Between? Towards Data Science · 15h ago
Research
**Know Who Spoke When: Build Real-Time, Multi-Speaker AI with NVIDIA Nemotron 3 Diarization** Hugging Face - Blog · 16h ago
Research
How GRPO Trains Small Language Models with Verifiable Rewards Towards Data Science · 17h ago
Research
Didactic knowledge or Clinical Cases? How Data Types Shape Medical Large Language Models cs.AI updates on arXiv.org · 1d ago
Research
An Affordable AI-Integrated Smart Cane for Multimodal Mobility Assistance of Visually Impaired Users cs.AI updates on arXiv.org · 1d ago
Research
PAANI : On Device Visual Evidence Fusion and Explainable Guidance for River Robot Simulation cs.AI updates on arXiv.org · 1d ago