Eigenform

Self-improving AI that learns from real-world consequences, not reward scores.

Eigenform is a Singapore-based AI research and engineering company (founded 2019 at NUS). We build local, empirically grounded recursive self-improvement systems: models that form hypotheses, test them in code against real data, and retrain on what survived. Our applied work is in geoscience and mineral exploration.

🌐 eigenform.ai · 💻 GitHub · 📄 Research · 𝕏 @EigenformAI · LinkedIn

Start here

Resource	What it is	Link
Groundtruth Dynamic Benchmark	Geology benchmark built from real exploration reports; answers graded 0–10 by an independent judge against source-anchored rubrics	Dataset · Leaderboard · Code
Groundtruth submissions	Model and harness results behind the leaderboard. Submit yours here	Dataset
Geocluster	Open-source, local-first AI workspace for geological analysis	GitHub · Try online
Survival is the Only Reward	Self-training without reward functions (negative-space learning)	arXiv:2601.12310

What we're working on

Negative-space learning: agents keep only strategies whose effects persist in a real environment, so there is no reward function to hack.
Continual learning in the field: in our geology experiment, 1,137 experiments produced 60 proven relationships, and training on the successful traces gave a +17.6% improvement over the base 7B open-weight model on a separate geology benchmark.
Dynamic benchmarking: a pipeline that reads any specialist corpus and generates a fresh exam (questions, answers, calibrated rubric), verified against the source. MIT-licensed.
Local compute: small models trained on your own hardware, so private data stays private.

Papers

Survival is the Only Reward: Sustainable Self-Training Through Environment-Mediated Selection (Jan 2026) · arXiv:2601.12310
Machine Learnability as a Measure of Order in Aperiodic Sequences (Aug 2025) · arXiv:2509.18103
Generalising from Self-Produced Data: Model Training Beyond Human Constraints (Apr 2025) · arXiv:2504.04711

Work with us

We partner with exploration companies and data holders, including AI earn-in joint ventures. Contact: ops@eigenform.ai