Papers3

All Beginner Intermediate Advanced

All Sources arXiv

#agentic tool use

DeepPlanning: Benchmarking Long-Horizon Agentic Planning with Verifiable Constraints

Intermediate

Yinger Zhang, Shutong Jiang et al.Jan 26arXiv

DeepPlanning is a new benchmark that tests whether AI can make long, realistic plans that fit time and money limits.

#long-horizon planning#agentic tool use#global constrained optimization

Not triaged yet

A Benchmark and Agentic Framework for Omni-Modal Reasoning and Tool Use in Long Videos

Intermediate

Mohammed Irfan Kurpath, Jaseel Muhammad Kaithakkodan et al.Dec 18arXiv

This paper builds a new test, LongShOTBench, to check if AI can truly understand long videos by using sight, speech, and sounds together.

#long-form video understanding#multimodal reasoning#audio-visual-speech alignment

Not triaged yet

INTELLECT-3: Technical Report

Intermediate

Prime Intellect Team, Mika Senghaas et al.Dec 18arXiv

INTELLECT-3 is a 106B-parameter Mixture-of-Experts model (about 12B active per token) trained with large-scale reinforcement learning and it beats many bigger models on math, coding, science, and reasoning tests.

#INTELLECT-3#prime-rl#verifiers

Not triaged yet