#Reasoning

8 articles with this tag

LLMs Lost in Transmission: Why Global Reasoning Fails
AI Research

LLMs Lost in Transmission: Why Global Reasoning Fails

A new paper reveals transformer LLMs struggle with complex global reasoning due to limited 'effective bandwidth,' solvable by Chain of Thought.

2 days ago
Uniqueness-Aware RL stops LLMs from getting lazy
AI Research

Uniqueness-Aware RL stops LLMs from getting lazy

Uniqueness-Aware RL prevents LLMs from converging on a single solution path by explicitly rewarding correct answers that employ rare problem-solving strategies.

about 1 month ago
Google Gemini 3 Redefines AI Reasoning and Efficiency
AI Research

Google Gemini 3 Redefines AI Reasoning and Efficiency

2 months ago
Google Gemini 3 Redefines Frontier AI Capabilities
AI Research

Google Gemini 3 Redefines Frontier AI Capabilities

2 months ago
DeepSeek V3.2 Release: Agent Focus Hits GPT-5 Level
AI Research

DeepSeek V3.2 Release: Agent Focus Hits GPT-5 Level

3 months ago
Claude Opus 4.5 Arrives, Dominating Code and Agents
AI Research

Claude Opus 4.5 Arrives, Dominating Code and Agents

3 months ago
Jeremy Berman’s Evolutionary Leap: Natural Language for ARC-AGI-2
AI Video

Jeremy Berman’s Evolutionary Leap: Natural Language for ARC-AGI-2

5 months ago
Unpacking AI's Invisible Rules: A Frog's Perspective
AI Video

Unpacking AI's Invisible Rules: A Frog's Perspective

6 months ago