Research

Papers

Research papers from arXiv and related sources

Total: 4513 AI/LLM: 2483 Testing: 2030
AI LLM

Quantitative Introspection in Language Models: Tracking Internal States Across Conversation

Tracking the internal states of large language models across conversations is important for safety, interpretability, and model welfare, yet current methods are limited. Linear probes and other whi...

Nicolas Martorell

2603.18893 2026-03-19
AI LLM

PromptHub: Enhancing Multi-Prompt Visual In-Context Learning with Locality-Aware Fusion, Concentration and Alignment

Visual In-Context Learning (VICL) aims to complete vision tasks by imitating pixel demonstrations. Recent work pioneered prompt fusion that combines the advantages of various demonstrations, which ...

Tianci Luo, Jinpeng Wang, Shiyu Qin, Niu Lian, Yan Feng, Bin Chen, Chun Yuan, Shu-Tao Xia

2603.18891 2026-03-19
AI LLM

Reasoning over mathematical objects: on-policy reward modeling and test time aggregation

The ability to precisely derive mathematical objects is a core requirement for downstream STEM applications, including mathematics, physics, and chemistry, where reasoning must culminate in formall...

Pranjal Aggarwal, Marjan Ghazvininejad, Seungone Kim, Ilia Kulikov, Jack Lanchantin, Xian Li, Tia...

2603.18886 2026-03-19
AI LLM

Geography According to ChatGPT -- How Generative AI Represents and Reasons about Geography

Understanding how AI will represent and reason about geography should be a key concern for all of us, as the broader public increasingly interacts with spaces and places through these systems. Simi...

Krzysztof Janowicz, Gengchen Mai, Rui Zhu, Song Gao, Zhangyu Wang, Yingjie Hu, Lauren Bennett

2603.18881 2026-03-19
AI LLM

A Human-in/on-the-Loop Framework for Accessible Text Generation

Plain Language and Easy-to-Read formats in text simplification are essential for cognitive accessibility. Yet current automatic simplification and evaluation pipelines remain largely automated, met...

Lourdes Moreno, Paloma Martínez

2603.18879 2026-03-19
AI LLM

Bridging Crystal Structure and Material Properties via Bond-Centric Descriptors

Although chemical bonding is the fundamental mechanistic bridge connecting atomic structure to macroscopic material properties, current data-driven materials science largely treats it as an implici...

Jian-Feng Zhang, Ze-Feng Gao, Xiao-Qi Han, Bo Zhan, Dingshun Lv, Miao Gao, Kai Liu, Xinguo Ren, Z...

2603.18876 2026-03-19
AI LLM

Evaluating LLM-Generated Lessons from the Language Learning Students' Perspective: A Short Case Study on Duolingo

Popular language learning applications such as Duolingo use large language models (LLMs) to generate lessons for its users. Most lessons focus on general real-world scenarios such as greetings, ord...

Carlos Rafael Catalan, Patricia Nicole Monderin, Lheane Marie Dizon, Gap Estrella, Raymund John S...

2603.18873 2026-03-19
AI LLM

Bridging Network Fragmentation: A Semantic-Augmented DRL Framework for UAV-aided VANETs

Vehicular Ad-hoc Networks (VANETs) are the digital cornerstone of autonomous driving, yet they suffer from severe network fragmentation in urban environments due to physical obstructions. Unmanned ...

Gaoxiang Cao, Wenke Yuan, Huasen He, Yunpeng Hou, Xiaofeng Jiang, Shuangwu Chen, Jian Yang

2603.18871 2026-03-19
AI LLM

Through the Looking-Glass: AI-Mediated Video Communication Reduces Interpersonal Trust and Confidence in Judgments

AI-based tools that mediate, enhance or generate parts of video communication may interfere with how people evaluate trustworthiness and credibility. In two preregistered online experiments (N = 2,...

Nelson Navajas Fernández, Jeffrey T. Hancock, Maurice Jakesch

2603.18868 2026-03-19
AI LLM

RewardFlow: Topology-Aware Reward Propagation on State Graphs for Agentic RL with Large Language Models

Reinforcement learning (RL) holds significant promise for enhancing the agentic reasoning capabilities of large language models (LLMs) with external environments. However, the inherent sparsity of ...

Xiao Feng, Bo Han, Zhanke Zhou, Jiaqi Fan, Jiangchao Yao, Ka Ho Li, Dahai Yu, Michael Kwok-Po Ng

2603.18859 2026-03-19
AI LLM

BeamAgent: LLM-Aided MIMO Beamforming with Decoupled Intent Parsing and Alternating Optimization for Joint Site Selection and Precoding

Integrating large language models (LLMs) into wireless communication optimization is a promising yet challenging direction. Existing approaches either use LLMs as black-box solvers or code generato...

Xiucheng Wang, Yue Zhang, Nan Cheng

2603.18855 2026-03-19
AI LLM

Tursio Database Search: How far are we from ChatGPT?

Business users need to search enterprise databases using natural language, just as they now search the web using ChatGPT or Perplexity. However, existing benchmarks -- designed for open-domain QA o...

Sulbha Jain, Shivani Tripathi, Shi Qiao, Alekh Jindal

2603.18835 2026-03-19
AI LLM

Student views in AI Ethics and Social Impact

An investigation, from a gender perspective, of how students view the ethical implications and societal effects of artificial intelligence is conducted, examining concepts that could have a big inf...

Tudor-Dan Mihoc, Manuela-Andreea Petrescu, Emilia-Loredana Pop

2603.18827 2026-03-19
AI LLM

Detecting Basic Values in A Noisy Russian Social Media Text Data: A Multi-Stage Classification Framework

This study presents a multi-stage classification framework for detecting human values in noisy Russian language social media, validated on a random sample of 7.5 million public text posts. Drawing ...

Maria Milkova, Maksim Rudnev

2603.18822 2026-03-19
AI LLM

ProRL Agent: Rollout-as-a-Service for RL Training of Multi-Turn LLM Agents

Multi-turn LLM agents are increasingly important for solving complex, interactive tasks, and reinforcement learning (RL) is a key ingredient for improving their long-horizon behavior. However, RL t...

Hao Zhang, Mingjie Liu, Shaokun Zhang, Songyang Han, Jian Hu, Zhenghui Jin, Yuchi Zhang, Shizhe D...

2603.18815 2026-03-19
AI LLM

Can LLM generate interesting mathematical research problems?

This paper is the second one in a series of work on the mathematical creativity of LLM. In the first paper, the authors proposed three criteria for evaluating the mathematical creativity of LLM and...

Xiaoyang Chen, Xiang Jiang

2603.18813 2026-03-19
AI LLM

Perceptio: Perception Enhanced Vision Language Models via Spatial Token Generation

Large Vision Language Models (LVLMs) excel at semantic understanding but struggle with fine grained spatial grounding, as the model must implicitly infer complex geometry without ever producing a s...

Yuchen Li, Amanmeet Garg, Shalini Chaudhuri, Rui Zhao, Garin Kessler

2603.18795 2026-03-19
AI LLM

Functional Subspace Watermarking for Large Language Models

Model watermarking utilizes internal representations to protect the ownership of large language models (LLMs). However, these features inevitably undergo complex distortions during realistic model ...

Zikang Ding, Junhao Li, Suling Wu, Junchi Yao, Hongbo Liu, Lijie Hu

2603.18793 2026-03-19
AI LLM

Mi:dm K 2.5 Pro

The evolving LLM landscape requires capabilities beyond simple text generation, prioritizing multi-step reasoning, long-context understanding, and agentic workflows. This shift challenges existing ...

KT Tech innovation Group

2603.18788 2026-03-19
AI LLM

Proceedings of the 2nd Workshop on Advancing Artificial Intelligence through Theory of Mind

This volume includes a selection of papers presented at the 2nd Workshop on Advancing Artificial Intelligence through Theory of Mind held at AAAI 2026 in Singapore on 26th January 2026. The purpose...

Nitay Alon, Joseph M. Barnby, Reuth Mirsky, Stefan Sarkadi

2603.18786 2026-03-19