arXiv cs.AI Weekly Report
Total: 609 papersDate: 2026-03-30 to 2026-04-05Category: cs.AI

Research Hot Topics

📁 Other (163 papers)

Other research directions

🤖 LLM Agents (155 papers)

Agent systems, multi-agent collaboration, autonomous decision making

📚 RAG Memory (84 papers)

Retrieval augmentation, dynamic indexing

🧠 Reasoning (75 papers)

Chain-of-thought, multi-step reasoning

🛡 Safety Alignment (68 papers)

Model safety, privacy, adversarial defense

🔋 Efficiency (36 papers)

Quantization, pruning, acceleration

Featured Papers

Why Aggregate Accuracy is Inadequate for Evaluating Fairness in Law Enforcement Facial Recognition Systems

Khalid Adnan Alsayed
Facial recognition systems are increasingly deployed in law enforcement and security contexts, where algorithmic decisions can carry significant societal consequences. Despite high reported accuracy, growing evidence demonstrates that such systems often exhibit uneven performance across demographic ...

The Ultimate Tutorial for AI-driven Scale Development in Generative Psychometrics: Releasing AIGENIE from its Bottle

Lara Russell-Lasalandra, Hudson Golino, Luis Eduardo Garrido, Alexander P. Christensen
Psychological scale development has traditionally required extensive expert involvement, iterative revision, and large-scale pilot testing before psychometric evaluation can begin. The `AIGENIE` R package implements the AI-GENIE framework (Automatic Item Generation with Network-Integrated Evaluation...

Dynamic Lookahead Distance via Reinforcement Learning-Based Pure Pursuit for Autonomous Racing

Mohamed Elgouhary, Amr S. El-Wakeel
Pure Pursuit (PP) is a widely used path-tracking algorithm in autonomous vehicles due to its simplicity and real-time performance. However, its effectiveness is sensitive to the choice of lookahead distance: shorter values improve cornering but can cause instability on straights, while longer values...

CirrusBench: Evaluating LLM-based Agents Beyond Correctness in Real-World Cloud Service Environments

Yi Yu, Guangquan Hu, Chenghuang Shen, Xingyan Liu, Jing Gu et al.
The increasing agentic capabilities of Large Language Models (LLMs) have enabled their deployment in real-world applications, such as cloud services, where customer-assistant interactions exhibit high technical complexity and long-horizon dependencies, making robustness and resolution efficiency cri...

FeDMRA: Federated Incremental Learning with Dynamic Memory Replay Allocation

Tiantian Wang, Xiang Xiang, Simon S. Du
In federated healthcare systems, Federated Class-Incremental Learning (FCIL) has emerged as a key paradigm, enabling continuous adaptive model learning among distributed clients while safeguarding data privacy. However, in practical applications, data across agent nodes within the distributed framew...

COvolve: Adversarial Co-Evolution of Large-Language-Model-Generated Policies and Environments via Two-Player Zero-Sum Game

Alkis Sygkounas, Rishi Hazra, Andreas Persson, Pedro Zuidberg Dos Martires, Amy Loutfi
A central challenge in building continually improving agents is that training environments are typically static or manually constructed. This restricts continual learning and generalization beyond the training distribution. We address this with COvolve, a co-evolutionary framework that leverages lar...

Deep Research of Deep Research: From Transformer to Agent, From AI to AI for Science

Yipeng Yu
With the advancement of large language models (LLMs) in their knowledge base and reasoning capabilities, their interactive modalities have evolved from pure text to multimodality and further to agentic tool use. Consequently, their applications have broadened from question answering to AI assistants...

CoE: Collaborative Entropy for Uncertainty Quantification in Agentic Multi-LLM Systems

Kangkang Sun, Jun Wu, Jianhua Li, Minyi Guo, Xiuzhen Che et al.
Uncertainty estimation in multi-LLM systems remains largely single-model-centric: existing methods quantify uncertainty within each model but do not adequately capture semantic disagreement across models. To address this gap, we propose Collaborative Entropy (CoE), a unified information-theoretic me...

Crossing the NL/PL Divide: Information Flow Analysis Across the NL/PL Boundary in LLM-Integrated Code

Zihao Xu, Xiao Cheng, Ruijie Meng, Yuekang Li
LLM API calls are becoming a ubiquitous program construct, yet they create a boundary that no existing program analysis can cross: runtime values enter a natural-language prompt, undergo opaque processing inside the LLM, and re-emerge as code, SQL, JSON, or text that the program consumes. Every anal...

Mapping data literacy trajectories in K-12 education

Robert Whyte, Manni Cheung, Katharine Childs, Jane Waite, Sue Sentance
Data literacy skills are fundamental in computer science education. However, understanding how data-driven systems work represents a paradigm shift from traditional rule-based programming. We conducted a systematic literature review of 84 studies to understand K-12 learners' engagement with data acr...

Top Authors

  • Kyeonghun Kim (5 papers)
  • Nam-Joon Kim (5 papers)
  • Hyuk-Jae Lee (5 papers)
  • Payal Fofadiya (5 papers)
  • Sunil Tiwari (5 papers)
  • Lei Wang (5 papers)
  • Youngung Han (4 papers)
  • Steven Y. Feng (4 papers)

Trends

  • Agent collaboration and autonomous decision making
  • Safety and alignment deep exploration
  • Reasoning capability breakthroughs
  • RAG architecture innovations
  • RL new paradigms (GRPO, policy distillation)

Data: arXiv cs.AI | Generated: 2026-04-05