RAG systems struggle with multi-hop reasoning. In most cases, the problem isn't the LLMs. It's the retrieval system. Standard RAG treats each piece of evidence as equally reliable, ignoring how documents connect to each other. Why is this a problem? When questions require
@dair_ai
-
Deep Reinforcement Learning for Multi-Agent Robot Coordination
By
–
Deep Reinforcement Learning for Multi-Agent Coordination Multi-agent reinforcement learning doesn't scale. The default approach to coordinating robot teams remains explicit communication or centralized training. This is inefficient. On the other hand, social insects solve this
-
Scaling Laws and Symmetry in Neural Networks Research
By
–
Scaling Laws and Symmetry The common belief is that scaling outperforms inductive biases. Give the model enough data and compute, and it will learn the structure on its own. But this new research finds the opposite. Researchers conducted comprehensive scaling experiments on
-
Improving RAG with Forward and Backward Lookup
By
–
Improving RAG with Forward and Backward Lookup This is a clever use of small and large language models. Traditional RAG systems compute similarity between the query and context chunks, retrieve the highest-scoring chunks, and then generate. But complex queries often lack
-
Frontier Models Struggle with Abstract Reasoning Tasks
By
–
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
-
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.