Announcing DiG-bench: Evaluating AI Discovery in Pure Text Environments
jcrwhittington · x · 2026-08-12
Researchers announce DiG-bench, a new benchmark designed to test the scientific discovery capabilities of AI. The benchmark evaluates frontier models through a series of text-based interactive discovery games.
By using a purely text-based environment, it probes discovery capabilities directly in the natural domain of language models without visual confounds. Results show that while frontier models have improved significantly recently, they are still stumped by some surprisingly simple problems.
Related event: DiG-bench: 70 Text Games Expose Frontier AI's Discovery Gaps(14 posts)→
More from Research
- DIRECT: retrieval-based next-question suggestions for conversational agents — burkov · 2026-10-16
- AI-Driven Timing-Aware Power Optimization Uses Learned Ranking With Baseline-Preserving Repair — Amit Sharma · 2026-10-16
- Waypoint-OPD: Alibaba Gates On-Policy Distillation via Early-Late Teacher Shift Agreement — Bingxi Hou · 2026-10-16
- MJev-Spatial: Single-Pass Classification Beats Autoregressive VLMs on Spatial Reasoning — mindlab-research · 2026-10-16
- MLExpert: 35B MoE Agent Trained to Autonomously Handle Machine Learning Engineering — Shangheng Du · 2026-10-16
- VLA-Δ: Zhejiang University Adds Physical State Transition Supervision to VLA Models — OmniAI-ZJU · 2026-10-16