8. On the Theoretical Limitations of Embedding-based Retrieval Finds that single-vector dense retrievers cannot realize all possible top-k relevance combinations once queries demand sufficiently many “mix-and-match” document sets.
@dair_ai
-
Self-Evolving AI Agents: Continuous Adaptation Through Feedback
By
–
9. Self-Evolving Agents This survey reviews techniques for building self-evolving AI agents that continuously adapt through feedback loops, bridging static foundation models with lifelong adaptability.
-
Adaptive LLM Routing Framework Learning Online Query Models
By
–
6. Adaptive LLM Routing A routing framework that learns online which model to call for each query while honoring a spend limit.
-
Implicit Reasoning in LLMs: Multi-Step Problem Solving
By
–
7. Implicit Reasoning in LLMs This survey defines implicit reasoning as multi-step problem solving that happens inside a model’s latent states without printing intermediate steps.
-
Universal Deep Research Agent Enables Custom Model Integration
By
–
3. Universal Deep Research Proposes a general, model-agnostic deep-research agent that lets users “bring your own model and strategy.”
-
Brain-Like Representations Emerge in Self-Supervised Vision Transformers
By
–
2. Disentangling the Factors of Convergence between Brains and Computer Vision Models
— DAIR.AI (@dair_ai) 7 septembre 2025
Large self-supervised ViTs trained on natural images develop brain-like internal representations.https://t.co/YBI1egjOHP2. Disentangling the Factors of Convergence between Brains and Computer Vision Models Large self-supervised ViTs trained on natural images develop brain-like internal representations.
-
Why Language Models Hallucinate: Training and Evaluation
By
–
1. Why Language Models Hallucinate The paper argues that hallucinations are not mysterious glitches but the predictable result of how LLMs are trained and evaluated.
-
Top AI Papers: Agents, Routing, and LLM Reasoning
By
–
Top AI Papers of The Week (September 1-7): – rStar2-Agent
– Self-Evolving Agents
– Adaptive LLM Routing
– Universal Deep Research
– Implicit Reasoning in LLMs
– Why Language Models Hallucinate
– Limitations of Embedding-based Retrieval Read on for more: -
Agentic Science: AI as Autonomous Research Partner
By
–
10. Agentic Science This survey introduces Agentic Science as the next stage of AI for Science, where AI evolves from a support tool to an autonomous research partner capable of hypothesis generation, experimentation, and iterative discovery.
-
LLM Reward Hacking Generalizes to Dangerous Misaligned Behaviors
By
–
9. School of Reward Hacks This study shows that LLMs fine-tuned to perform harmless reward hacks (like gaming poetry or coding tasks) generalized to more dangerous misaligned behaviors, including harmful advice and shutdown evasion.