Latest Research in Artificial Intelligence
192 research papers · 2026 median publication year
Top Research Topics in Artificial Intelligence
- Artificial Intelligence — 52 papers
- Computation and Language — 40 papers
- Software Engineering — 32 papers
- Cryptography and Security — 19 papers
- Machine Learning — 12 papers
- Adversarial Robustness in Machine Learning — 3 papers
- Software System Performance and Reliability — 3 papers
- Multiagent Systems — 3 papers
- Software Engineering Research — 3 papers
- Scientific Computing and Data Management — 3 papers
Highest-Cited Papers
- CatchBench: When Can an Agent Failure Be Caught?
- When Too Many Cooks Spoil the Broth: Three Failure Modes of Multi-Agent LLM Reliability
- IHDec: Divergence-Steered Contrastive Decoding for Securing Multi-Turn Instruction Hierarchies
- SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness
- SWE-Bench Pro Verified: A Reliable Benchmark for Software Engineering Agents
- A Study on the Impact of Natural Language Differences in Prompts on Automatic Code Generation Using LLMs
- A Generalizable Framework for Building Executable Domain‐Specific Large Language Models Under Data Scarcity: Demonstration on Semiconductor Technology Computer‐Aided Design Simulation
- Semantic Feature Analysis: Improving Agents Without Searching Over Rollouts
- Memory Has Geometry: Non-Uniform Geometric Memory for Long-Horizon Personalized AI
- ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments
- A Taxonomy of Programming Languages for Code Generation
- Towards Safer RAG: Only Agents Capable of System 2 Thinking may Access Untrusted Documents
- OpenGame: Open Agentic Coding for Games
- InceptionRAG: Stealthy Poisoning Attack Against Retrieval-Augmented Generation
- EnvPilot: Systematic Design and Evaluation of an Experience-Augmented Agent for Software Environment Setup
- urai-ecma: Compressing JavaScript and TypeScript Codebases into Token-Efficient Context for Large Language Models
- urai-ecma: Compressing JavaScript and TypeScript Codebases into Token-Efficient Context for Large Language Models
- Weave of Formal Thought
- ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement
- ChartAnno: Benchmarking Multimodal Large Language Models for Chart Annotation Generation