document-reasoning

Tag

Cards List
#document-reasoning

AdaThinking-E: One-Token Entropy Regulation for Adaptive Thinking

arXiv cs.CL · 2026-08-28 Cached

The article proposes AdaThinking-E, a reinforcement learning framework that uses one-token entropy regulation to enable adaptive thinking in multimodal large language models, improving accuracy on complex tasks and efficiency on simple ones.

0 favorites 0 likes
#document-reasoning

AGORA: An Archive-Grounded Benchmark for Agentic Workplace Document Reasoning

arXiv cs.CL · 2026-06-24 Cached

AGORA is a new benchmark for evaluating large language models on archive-grounded reasoning tasks across workplace documents, comprising 362 questions over 9,664 real documents. The strongest model achieves only 59.4% accuracy, highlighting substantial room for improvement.

0 favorites 0 likes
← Back to home

Submit Feedback