SCI-AGENT-EXAM: Benchmarking Agents on Scientific Research Tasks

23 Oct 2026Reported by arXiv21

SCI-AGENT-EXAM: Benchmarking Agents on Scientific Research Tasks. It centres on Benchmarks, and also names GPT and GitHub. Reported by arXiv. Bharat Hunt files it under AI Research and AI Models — the section covering papers, benchmarks, evaluations, interpretability and safety results.

Written by Bharat Hunt from the headline and the coverage below. The original reporting is the source of truth.

Read original coverage

Companies, models and people in this story

Reported by arXiv

First seen 23 oct 2026

arXivSCI-AGENT-EXAM: Benchmarking Agents on Scientific Research Tasks23 Oct 2026Tianyun Zhong

AI Models39

OpenAI is open to slowing AI development: Sam Altman tells staff

OpenAI is open to slowing AI development: Sam Altman tells staff. The story centres on OpenAI. 4 sources have covered it so far, including Inc42, The Economic Times and bloomberg.com. Bharat Hunt files it under AI Models — the section covering a new or updated model, its capabilities, benchmarks or availability.

Inc4212 Sept 2026Covered by 4 sources

AI Models23

Helping older adults use AI in everyday life

Helping older adults use AI in everyday life. It centres on OpenAI, and also names GPT. Reported by OpenAI. Bharat Hunt files it under AI Models — the section covering a new or updated model, its capabilities, benchmarks or availability.

← All AI stories

SCI-AGENT-EXAM: Benchmarking Agents on Scientific Research Tasks

Companies, models and people in this story

Reported by arXiv

OpenAI is open to slowing AI development: Sam Altman tells staff

Helping older adults use AI in everyday life

Perplexity trusts GPT-6 Astra with end-to-end systems

Cognition helps Devin test its own work with GPT‑6 Astra

Companies, models and people in this story

Reported by arXiv

Related AI coverage

OpenAI is open to slowing AI development: Sam Altman tells staff

Helping older adults use AI in everyday life

Perplexity trusts GPT-6 Astra with end-to-end systems

Cognition helps Devin test its own work with GPT‑6 Astra