Article
From Benchmarks to Cognitive Landscapes: Building ReasonScape
By
•
•
4Mike Ravkine PRO
mike-ravkine
AI & ML interests
LLM Research / Development / Evaluation
Recent Activity
posted
an
update
4 days ago
"Do LLMs Really Need 10+ Thoughts for "Find the Time 1000 Days Later"? Towards Structural Understanding of LLM Overthinking"
https://arxiv.org/abs/2510.07880
> Our analysis reveals two major patterns for open-weight thinking models -- Explorer and Late Landing. This finding provides evidence that over-verification and over-exploration are the primary drivers of overthinking in LLMs. Grounded in thought structures, we propose a utility-based definition of overthinking, which moves beyond length-based metrics. This revised definition offers a more insightful understanding of LLMs' thought progression, as well as practical guidelines for principled overthinking management.
Really cool paper! Unfortunately no code, may need to attempt to recreate my own TRACE 🤔
liked
a model
6 days ago
noctrex/cogito-v2-preview-llama-109B-MoE-MXFP4_MOE-GGUF
liked
a model
6 days ago
deepcogito/cogito-v2-preview-llama-70B
Organizations
None yet
published
an
article
12 days ago
published
an
article
4 months ago
Article
Accidentally Building an AI Reasoning Research Ecosystem (Or: Can AI Stop Thinking?)
By
•
•
3