CMU team releases SMDD-Bench: 502 small-molecule drug design tasks for RL agents
willcb · x · 2026-10-03
A year after pivoting to AI for molecule design and drug discovery, Niloofar Gheini's CMU team, together with PrimeIntellect, released SMDD-Bench and its training environments.
- Scale: 502 small-molecule design tasks with RDKit, ADMET-AI, and Boltz-2 in the loop, available on PrimeIntellect's Environments Hub, ready to train with prime-rl.
- Motivation: RL needs long-horizon tasks beyond math and coding; drug design adds open problems in long-horizon planning, exploration, and learning from imperfect feedback.
- Findings: 1) Harness optimization goes a long way in scientific tasks, and progress is still bottlenecked by model capabilities rather than knowledge; 2) Automating harness optimization works in some cases but not others.
A notable effort to extend RL/agent evaluation into the sciences.
More from Research
- Genome-scale ORF screen finds NKX2-5 restores vision in aged mice — anshulkundaje · 2026-10-03
- Hutter Prize sees biggest progress in 20 years: three winners, ~10% total gain in one month — mhutter42 · 2026-10-03
- MolmoMotion: AI2's 4B VLM forecasts 3D point trajectories from language instructions — rsasaki0109 · 2026-10-03
- Unitree's UnifoLM-WLA-1.0: one 6B model for 64 whole-body humanoid tasks — WebAssemblyMan · 2026-10-03
- Mathematician Kontorovich admits he was wrong about AI autonomously formalizing math — AlexKontorovich · 2026-10-03
- New paper: training LLMs to verbalize when they know they're being evaluated — xuanalogue · 2026-10-03