Discovery under Hypothesis Redundancy: A Geometric Theory of Discovery Bottlenecks

• URL: http://arxiv.org/abs/2606.14386v1
• Date: Fri, 12 Jun 2026 12:21:09 GMT
• Title: Discovery under Hypothesis Redundancy: A Geometric Theory of Discovery Bottlenecks
• Abstract summary: We study hybrid discovery systems that combine structured local search with LLM-generated non-local proposals.<n>We formalize three geometric conditions for hybrid advantage, derive necessary conditions for hybrid advantage, and test the mechanism.<n>The framework turns LLM-guided discovery from generic novelty search into a diagnostic procedure for deciding when directed non-local exploration is warranted.
• Score: 3.929022620607768
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Scientific discovery saturates when new hypotheses cease to provide independent information, even if the nominal hypothesis space remains large. We study hybrid discovery systems that combine structured local search with LLM-generated non-local proposals and pose the Search Compression Hypothesis: non-local exploration helps only when three geometric conditions co-occur: spectral compression, orthogonal escape from the explored span, and residual signal alignment with the target. We formalize these conditions, derive necessary conditions for hybrid advantage, and test the mechanism in controlled synthetic environments, large-scale A-share factor discovery, and symbolic-regression benchmarks; a public tabular operational sanity check tests the associated budget-allocation implication. Signal-planting and directed-versus-random experiments show that novelty alone is insufficient: random orthogonal jumps expand coverage but do not improve yield without predictive alignment. Across compression sweeps, real factor archives, and LLM-SRBench tasks, hybrid gains concentrate in weakly represented but target-bearing directions and vanish as the hypothesis space approaches full rank. The framework turns LLM-guided discovery from generic novelty search into a diagnostic procedure for deciding when directed non-local exploration is warranted.

Related papers

• Autonomous Scientific Discovery via Iterative Meta-Reflection [44.46230654454998]
  We introduce DiscoPER, a framework that conducts open-ended research by dynamically generating and executing code to explore datasets without pre-specified research objectives.<n>By treating prior discoveries as empirical data, DiscoPER actively redirecting hypothesis exploration toward uncharted regions of the search space.<n> evaluated on iNatDisco, a new multimodal ecological knowledge benchmark with pattern-level ground truth obtained from peer-reviewed literature.
  arXiv  Detail & Related papers  (2026-07-01T16:16:07Z)
• CANN-EUCLID: unsupervised constitutive artificial neural network model discovery from full-field data [0.0]
  Constitutive artificial neural networks (CANNs) provide interpretable material model discovery.<n>CANNs have so far been used in stress-inducing settings based on apparent stress-strain data from homogeneous tests.<n>Here, we combine CANNs with the stress-unsupervised full-field discovery framework EUCLID to identify sparse hyperelastic laws.
  arXiv  Detail & Related papers  (2026-06-12T15:44:06Z)
• Agreement in Representation Space for Open-Ended Self-Consistency [7.4508858982186]
  We study self-consistency in open-ended generation tasks such as code synthesis and text summarization.<n>We introduce Embedding-Based Agreement (EBA), a training-free operationalization that estimates agreement by clustering sampled generations in embedding space.<n>EBA consistently outperforms random selection and exhibits more stable scaling behavior than recent selection approaches.
  arXiv  Detail & Related papers  (2026-06-10T12:26:49Z)
• All Circuits Lead to Rome: Rethinking Functional Anisotropy in Circuit and Sheaf Discovery for LLMs [61.02007370456733]
  We show that a single task can be supported by multiple, structurally distinct circuits or sheaves that are simultaneously faithful, sparse, and complete.<n>We propose a Distributive Circuit Hypothesis and provide a theoretical analysis demonstrating that non-unique, low-overlap circuit explanations arise naturally from high-dimensional superposition.
  arXiv  Detail & Related papers  (2026-05-12T19:21:23Z)
• LLM-Guided Open Hypothesis Learning from Autonomous Scanning Probe Microscopy Experiments [3.783505208172849]
  We introduce an open hypothesis-learning framework that combines symbolic regression with large-language-model-based physical evaluation.<n>We demonstrate the approach on autonomous piezoresponse force microscopy measurements of ferroelectric domain switching in a PZT thin film.
  arXiv  Detail & Related papers  (2026-05-07T18:44:46Z)
• GTS: Inference-Time Scaling of Latent Reasoning with a Learnable Gaussian Thought Sampler [54.10960908347221]
  We model latent thought exploration as conditional sampling from learnable densities and instantiate this idea as a Gaussian Thought Sampler (GTS)<n>GTS predicts context-dependent perturbation distributions over continuous reasoning states and is trained with GRPO-style policy optimization while keeping the backbone frozen.
  arXiv  Detail & Related papers  (2026-02-15T09:57:47Z)
• HypoSpace: Evaluating LLM Creativity as Set-Valued Hypothesis Generators under Underdetermination [46.896452542901805]
  We introduce HypoSpace, a diagnostic suite that treats LLMs as samplers of finite hypothesis sets.<n>We instantiate HypoSpace in three structured domains with deterministic validators and exactly enumerated hypothesis spaces.<n>Across instruction-tuned and reasoning-focused models, Validity often remains high while Uniqueness and Recovery degrade as the admissible space grows.
  arXiv  Detail & Related papers  (2025-10-17T13:00:32Z)
• Hypothesis Hunting with Evolving Networks of Autonomous Scientific Agents [52.50038914857797]
  We term this process hypothesis hunting: the cumulative search for insight through sustained exploration across vast and complex hypothesis spaces.<n>We introduce AScience, a framework modeling discovery as the interaction of agents, networks, and evaluation norms, and implement it as ASCollab.<n> Experiments show that such social dynamics enable the accumulation of expert-rated results along the diversity-quality-novelty frontier.
  arXiv  Detail & Related papers  (2025-10-08T08:47:07Z)
• MOOSE-Chem2: Exploring LLM Limits in Fine-Grained Scientific Hypothesis Discovery via Hierarchical Search [102.11776494401705]
  Large language models (LLMs) have shown promise in automating scientific hypothesis generation.<n>Existing approaches primarily yield coarse-grained hypotheses lacking critical methodological and experimental details.<n>We introduce and formally define the new task of fine-grained scientific hypothesis discovery.
  arXiv  Detail & Related papers  (2025-05-25T16:13:46Z)
• Optimal Multi-Distribution Learning [88.3008613028333]
  Multi-distribution learning seeks to learn a shared model that minimizes the worst-case risk across $k$ distinct data distributions.<n>We propose a novel algorithm that yields an varepsilon-optimal randomized hypothesis with a sample complexity on the order of (d+k)/varepsilon2.
  arXiv  Detail & Related papers  (2023-12-08T16:06:29Z)
• Experimental demonstration of genuine tripartite nonlocality under strict locality conditions [16.812051020169257]
  Nonlocality captures one of the counterintuitive features of nature that defies classical intuition. Recent investigations reveal that our physical world's nonlocality is at least tripartite. We experimentally demonstrate such genuine tripartite nonlocality in a network under strict locality constraints.
  arXiv  Detail & Related papers  (2022-03-02T06:08:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.