Latest Research in Artificial Intelligence

192 research papers · 2026 median publication year

Top Research Topics in Artificial Intelligence

Highest-Cited Papers

  1. CatchBench: When Can an Agent Failure Be Caught?
  2. When Too Many Cooks Spoil the Broth: Three Failure Modes of Multi-Agent LLM Reliability
  3. IHDec: Divergence-Steered Contrastive Decoding for Securing Multi-Turn Instruction Hierarchies
  4. SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness
  5. SWE-Bench Pro Verified: A Reliable Benchmark for Software Engineering Agents
  6. A Study on the Impact of Natural Language Differences in Prompts on Automatic Code Generation Using LLMs
  7. A Generalizable Framework for Building Executable Domain‐Specific Large Language Models Under Data Scarcity: Demonstration on Semiconductor Technology Computer‐Aided Design Simulation
  8. Semantic Feature Analysis: Improving Agents Without Searching Over Rollouts
  9. Memory Has Geometry: Non-Uniform Geometric Memory for Long-Horizon Personalized AI
  10. ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments
  11. A Taxonomy of Programming Languages for Code Generation
  12. Towards Safer RAG: Only Agents Capable of System 2 Thinking may Access Untrusted Documents
  13. OpenGame: Open Agentic Coding for Games
  14. InceptionRAG: Stealthy Poisoning Attack Against Retrieval-Augmented Generation
  15. EnvPilot: Systematic Design and Evaluation of an Experience-Augmented Agent for Software Environment Setup
  16. urai-ecma: Compressing JavaScript and TypeScript Codebases into Token-Efficient Context for Large Language Models
  17. urai-ecma: Compressing JavaScript and TypeScript Codebases into Token-Efficient Context for Large Language Models
  18. Weave of Formal Thought
  19. ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement
  20. ChartAnno: Benchmarking Multimodal Large Language Models for Chart Annotation Generation
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
L3 Region - - 2026 Sep Q3

Artificial Intelligence

192 papers

Top Topics (10)

Artificial Intelligence52
Computation and Language40
Software Engineering32
Cryptography and Security19
Machine Learning12
Adversarial Robustness in Machine Learning3
Software System Performance and Reliability3
Multiagent Systems3
Software Engineering Research3
Scientific Computing and Data Management3

Top Publications (20)

1.CatchBench: When Can an Agent Failure Be Caught?2.When Too Many Cooks Spoil the Broth: Three Failure Modes of Multi-Agent LLM Reliability3.IHDec: Divergence-Steered Contrastive Decoding for Securing Multi-Turn Instruction Hierarchies4.SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness5.SWE-Bench Pro Verified: A Reliable Benchmark for Software Engineering Agents6.A Study on the Impact of Natural Language Differences in Prompts on Automatic Code Generation Using LLMs7.A Generalizable Framework for Building Executable Domain‐Specific Large Language Models Under Data Scarcity: Demonstration on Semiconductor Technology Computer‐Aided Design Simulation8.Semantic Feature Analysis: Improving Agents Without Searching Over Rollouts9.Memory Has Geometry: Non-Uniform Geometric Memory for Long-Horizon Personalized AI10.ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments11.A Taxonomy of Programming Languages for Code Generation12.Towards Safer RAG: Only Agents Capable of System 2 Thinking may Access Untrusted Documents13.OpenGame: Open Agentic Coding for Games14.InceptionRAG: Stealthy Poisoning Attack Against Retrieval-Augmented Generation15.EnvPilot: Systematic Design and Evaluation of an Experience-Augmented Agent for Software Environment Setup16.urai-ecma: Compressing JavaScript and TypeScript Codebases into Token-Efficient Context for Large Language Models17.urai-ecma: Compressing JavaScript and TypeScript Codebases into Token-Efficient Context for Large Language Models18.Weave of Formal Thought19.ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement20.ChartAnno: Benchmarking Multimodal Large Language Models for Chart Annotation Generation
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.