Bake AI's Two Agent Benchmark Papers Accepted by NeurIPS 2026

Bake AI announced that two of its papers, NARRA-Gym (an executable environment testing LLM agents' long-horizon narrative coherence, with significant gaps among nine frontier models) and JobBench (covering 130 tasks), have been accepted by NeurIPS 2026.

2026-09-26 ~ 2026-09-26 · 2 related posts

• Bake AI lands two NeurIPS 2026 papers: NARRA-Gym and JobBench with 130 tasks across 35 occupations — my_cat_can_code · 2026-09-26
• NARRA-Gym: New Benchmark Finds Frontier LLMs Vary Widely on Long-Horizon Interactive Storytelling — my_cat_can_code · 2026-09-26