Self-correcting search in generative design

Iterative feedback steering that improves candidate success rates across materials, proteins, and drugs through internal-state control, achieving 4-6x empirical gains.

9 members. Each node is clickable.

Loading graph…

Drawn from 3 sources

The papers/notes whose extracted claims & findings make up this cluster.

Using Self-Correcting Search to Accelerate Materials Discovery7 members
Emergent Introspective Awareness in Large Language Models1 member
SFR-DeepResearch: Towards Effective Reinforcement Learning for Autonomously Reasoning Single Agents1 member

Bridges (4)

Other communities that share members with this one — cross-cutting threads or papers that sit at the seam between two themes.

Manifold-aware concept steering in neural representations9 shared
Self-correcting search optimization2 shared
Intentional control of mental representations1 shared
MatterGen crystal generation benchmarks1 shared

Claims (5)

Internal-state feedback steering is applicable to protein design and drug discovery beyond materials.Generalizes the mechanism to other molecular design domains.
Self-correcting search applicable to protein design / drug discoveryClaim by the authors that the self-correcting search method can be extended to protein design and drug discovery.
Self-correcting search employs the same conceptual move as Wurgaft's manifold steering, applied to chemistry instead of LMsInterpretive assertion that the internal-state feedback mechanism mirrors manifold steering from prior work.
Self-correcting search improves viable candidate success rate from 6.5% to ~30% (4.6x improvement)Interpretive claim that the method dramatically boosts success rate over the MatterGen baseline.
Self-correcting search is Pareto-optimal across tested conditioning strengths.Asserts that the method maintains efficiency across a range of constraint strengths without degradation.

Findings (4)

Baseline MatterGen achieves 6.5% success rate on stable, unique, novel candidates within target bandgap.Quantitative baseline establishing the performance floor for self-correcting search improvements.
Intentional Control of Internal StatesModels can modulate their internal representations when instructed or incentivized to 'think about' a concept; effect replicates across all tested models regardless of capability.
Self-correcting search yields ~+30% improvement in viable candidates within target bandgap range.Main empirical result: interpretability-driven feedback increases discovery efficiency significantly.
SFR-DR-20B achieves 28.7% on Humanity's Last Exam full text-only benchmark, 65% relative improvement over gpt-oss-20b baseline.Main evaluation result showing best variant outperforms many proprietary and open-source baselines of comparable or larger sizes.