Here are the top AI Papers of the Week (May 19 – 25): – ARC-AGI-2
– AdaptThink
– EfficientLLM
– Visual Planning
– The Pitfalls of Reasoning
– Teaching MLLMs to Think with Images Here is the full list:
@dair_ai
-
Top AI Research Papers of the Week: May 19-25
By
–
-
CellVerse: LLM Benchmark for Single-Cell Biology Tasks
By
–
10. CellVerse Introduces a benchmark to evaluate LLMs on single-cell biology tasks by converting multi-omics data into natural language.
-
AI Agents vs Agentic AI: Architecture and Capabilities Review
By
–
9. AI Agents vs. Agentic AI This review paper distinguishes AI Agents from Agentic AI, presenting a structured taxonomy and comparing their architectures, capabilities, and challenges.
-
DiskANN Vector Search Integration in Azure Cosmos DB
By
–
8. Cost-Efficient, Low-Latency Vector Search Integrates DiskANN (a vector indexing library) inside of Azure Cosmos DB NoSQL (an operational dataset) that uses a single vector index per partition stored in existing index trees.
-
RL Framework Teaches LLMs Efficient Search Tool Usage
By
–
7. RL for Search-Efficient LLMs Proposes a new RL-based framework (SEM) that explicitly teaches LLMs when to invoke search and when to rely on internal knowledge, aiming to reduce redundant tool use while maintaining answer accuracy.
-
HealthBench: 5,000 Multi-Turn Medical Conversations Benchmark
By
–
5. HealthBench HealthBench is a benchmark of 5,000 multi-turn health conversations graded against 48,562 rubric criteria written by 262 physicians across 60 countries.
-
Nemotron-Research-Tool-N1: LLM Tool-Using with Rule-Based RL
By
–
6. Nemotron-Research-Tool-N1 Introduces Tool-N1, a family of tool-using LLMs trained using a rule-based reinforcement learning (R1-style RL) approach, without reliance on supervised reasoning trajectories.
-
AM-Thinking-v1: 32B Open-Source Model Rivaling Larger MoE Systems
By
–
4. AM-Thinking-v1 Introduces a dense, open-source 32B language model that achieves state-of-the-art performance in reasoning tasks, rivaling significantly larger Mixture-of-Experts (MoE) models.
-
RL Improves LLM Mathematical Reasoning with Single Example
By
–
3. RL for Reasoning in LLMs with One Training Example This paper shows that Reinforcement Learning with Verifiable Rewards (RLVR) can significantly improve mathematical reasoning in LLMs even when trained with just a single example.
-
LLMs Performance Degradation in Multi-Turn Conversations
By
–
2. LLMs Get Lost in Multi-Turn Conversation Investigates how top LLMs degrade in performance during underspecified, multi-turn interactions, common in real-world usage but rarely evaluated.