Clusters
-
Language Understanding and Social Cognition
This cluster covers how LLMs process, reason about, and align with human language, values, and social norms. Researchers study model limitations, discourse comprehension, argumentation, sentiment, persona, and the broader societal implications of AI language behavior.
434 notes · 1247 papers -
Reinforcement Learning for Reasoning
Research on training language models to reason using reinforcement learning, reward models, and test-time compute scaling. Covers RLVR, self-refinement, inference-time search, and how RL reshapes model behavior and reasoning capabilities.
278 notes · 765 papers -
Reasoning Architectures and Cognition
Research on how language models reason internally, including chain-of-thought methods, novel architectures for inference, mechanistic interpretability, and cognitive-inspired memory systems. Studies both the design of reasoning systems and what actually happens inside models when they think.
260 notes · 820 papers -
Agentic Systems and Planning
Research on designing, architecting, and evaluating AI agents that plan and execute complex tasks, including multi-agent coordination, tool use, autonomous decision-making, and benchmarks for assessing real-world agent readiness.
195 notes · 356 papers -
Conversational AI Psychology
Research on the psychological dimensions of human-AI interaction, including therapeutic chatbots, empathy modeling, emotional understanding, and user behavior. Studied by researchers at the intersection of clinical psychology, human-computer interaction, and natural language processing.
132 notes · 162 papers -
Recommender Systems
Research on building and improving systems that suggest content, products, or information to users. Covers neural architectures, conversational interfaces, LLM-based approaches, and personalization techniques for recommendation.
89 notes · 107 papers -
Conversational AI Systems
Research on building and evaluating dialogue systems, conversational agents, and interactive assistants. Covers multi-turn conversation architecture, personalization, synthetic dialog generation, and challenges like context degradation and proactive agent behavior.
68 notes · 266 papers -
Knowledge Retrieval and Reasoning
Research on how AI systems acquire, store, and retrieve structured and unstructured knowledge to answer questions and generate informed responses. Covers RAG architectures, knowledge graphs, domain specialization, and the integration of external information into language model reasoning.
62 notes · 322 papers -
Applied AI and Human Collaboration
Research on how AI systems are deployed in real-world professional, creative, and educational contexts. Covers human-AI co-writing, domain-specific applications, and the social and cognitive dynamics that emerge when language models interact with users.
46 notes · 104 papers