NEW research on abstract reasoning. Frontier models like GPT-5 and Grok 4 still can't do what humans find trivially easy: infer transformation rules from a handful of examples. The default approach to solving ARC-AGI (the leading benchmark for abstract reasoning) treats these
@dair_ai
-
Meta Research Challenges Chain-of-Thought Reasoning Approach
By
–
NEW Research from Meta Superintelligence Labs and collaborators. The default approach to improving LLM reasoning today remains extending chain-of-thought sequences. Longer reasoning traces aren't always better. Longer traces conflate reasoning depth with sequence length and
-
RouteRAG: Adaptive Retrieval for Multi-Hop Reasoning Systems
By
–
Adaptive retrieval is the way to go! And this RouteRAG paper shows why. Let's talk about it: RAG systems have a retrieval problem. The default approach to multi-hop reasoning today relies on fixed retrieval pipelines. It typically involves fetching text + maybe graph data, and
-
ProAgent: First Proactive LLM Agent System with AR Integration
By
–
10. ProAgent ProAgent is the first end-to-end proactive LLM agent system that harnesses sensory contexts from AR glasses, smartphones, and edge servers to deliver assistance without explicit user instructions.
-
AI Agent Adoption Study: Perplexity Comet Browser Insights
By
–
9. AI Agent Adoption Study Presents the first large-scale field study of AI agent adoption using hundreds of millions of anonymized interactions from Perplexity’s Comet browser.
-
Cognitive Foundations for Reasoning in Large Language Models
By
–
10. Cognitive Foundations for Reasoning in LLMs Develops a taxonomy of 28 cognitive elements and evaluate 192K reasoning traces from 18 models, plus human think-aloud traces.
-
Multi-Agent Collaboration Enables Multimodal LLM Vision Integration
By
–
9. Multi-Agent Collaboration for Multimodal LLMs introduces a framework where vision models serve as “eyes” for language models through multi-agent collaboration.
-
Anthropic Evaluates Honesty and Lie Detection in AI Models
By
–
8. Evaluating Honesty and Lie Detection in AI Models Anthropic researchers evaluate honesty and lie detection techniques across five testbed settings where models generate statements they believe to be false.
-
Training Smaller LLMs with Frontier Model Reasoning Traces
By
–
7. Training LLMs with Reasoning Traces Ivestigates how reasoning traces from frontier models like DeepSeek-R1 and GPT-OSS can improve smaller language models through post-training.
-
Evolution Strategies Enable Backprop-Free Optimization Billion-Parameter Networks
By
–
6. Evolution Strategies at Hyperscale An evolution strategies algorithm designed to scale backprop-free optimization to large population sizes for billion-parameter neural networks.