Here are the top AI Papers of the Week (Feb 24 – Mar 2): – GPT-4.5
– PlanGEN
– Protein LLMs
– Chain-of-Draft
– Claude 3.7 Sonnet
– Emergent Misalignment Read on for more:
@dair_ai
-
Top AI Papers of the Week: GPT-4.5, Claude 3.7, and More
By
–
-
Google Introduces PlanGEN Framework for Enhanced LLM Planning
By
–
Google presents PlanGEN for complex planning and reasoning. PlanGEN is a multi-agent framework designed to enhance planning and reasoning in LLMs through constraint-guided iterative verification and adaptive algorithm selection. Key insights include: Constraint-Guided
-
LLMs Learn from Feedback During Test-Time Inference
By
–
Learning to Reason from Feedback at Test-Time This new paper proposes a new paradigm called FTTT (Feedback-based Test-Time Training) that enables LLMs to learn iteratively from environment feedback during inference. Key highlights include: • Test-time optimization for
-
The Danger of Overthinking in Large Reasoning Models
By
–
9). The Danger of Overthinking – This paper investigates overthinking in Large Reasoning Models (LRMs)—a phenomenon where models prioritize extended internal reasoning over interacting with their environment.
-
Inner Thinking Transformers: Scaling Reasoning in Small LLMs
By
–
10). Inner Thinking Transformers – A new method that enhances reasoning efficiency in small-scale LLMs via dynamic depth scaling. ITT aims to mitigate parameter bottlenecks in LLMs, providing scalable reasoning efficiency without expanding model size.
-
MoBA: New Attention Mechanism for Efficient Long-Context LLMs
By
–
8). MoBA – A new attention mechanism that enhances efficiency in handling long-context sequences for LLMs while maintaining strong performance.
-
Open-Reasoner-Zero: Efficient RL Framework Outperforms DeepSeek-R1
By
–
7). Open-Reasoner-Zero – an open-source large-scale minimalist RL framework to enhance reasoning. Achieves significant scalability requiring only 1/30th of the training steps of DeepSeek-R1-Zero-Qwen-32B to outperform it on GPQA Diamond.
-
Text Data Augmentation Techniques for Large Language Models
By
–
10). Survey: Text Data Augmentation for LLMs This comprehensive survey covers text data augmentation techniques for LLMs.
-
Enhancing Reasoning Capabilities in Large Language Models
By
–
9). Advancing Reasoning in LLMs This survey paper provides a timely overview of emerging methods to enhance reasoning capabilities in LLMs.
-
MaAS: Universal Agentic Supernet for Dynamic Agent Teams
By
–
8). MaAS MaAS (Multi-agent Architecture Search) learns a universal “agentic supernet” from which it can spawn an optimal agent team on the fly for each query.