Before the Action: Benchmarking LLMs on Prospective Hypothesis Discovery
Large language models (LLMs) excel at answering pre-specified questions, yet their ability to navigate the open-ended, pre-conclusion stage of discovery remains largely unmeasured. This paper introduces Prospective Hypothesis Discovery (PHD), which asks models to autonomously construct grounded, discriminative, and testable hypothesis spaces from inconclusive evidence. To evaluate this, they present HypoArena, comprising HypoData (988 cases across six domains) and HypoEval (an evaluation framework). Experiments on 15 frontier LLMs reveal clear capability stratification and model-dependent effects of structured analytical skills, with gains for some lower-performing models but regressions for others, including a top performer. Arena evaluation resolves finer-grained differences and shows strong agreement with human experts.
-->
[Submitted on 17 Jul 2026]
Title:Before the Action: Benchmarking LLMs on Prospective Hypothesis Discovery
View a PDF of the paper titled Before the Action: Benchmarking LLMs on Prospective Hypothesis Discovery, by Tianyun Zhong and 17 other authors
View PDF HTML (experimental)
Abstract:Large language models (LLMs) excel at answering pre-specified questions, yet their ability to navigate the open-ended, pre-conclusion stage of discovery remains largely unmeasured. We introduce Prospective Hypothesis Discovery (PHD), which asks models to autonomously construct grounded, discriminative, and testable hypothesis spaces from inconclusive evidence, including anomalous observations and fragmented records, to guide subsequent investigation. To evaluate this capability, we introduce HypoArena, comprising HypoData, a benchmark of 988 cases across six scientific and analytical domains, and HypoEval, an evaluation framework for open-ended hypothesis sets. To construct HypoData at scale, we propose Retrospective Context Regression, a Forge--Audit pipeline that reconstructs pre-conclusion contexts from completed expert documents by removing explicit conclusions, target hypotheses, and retrospective causal attributions while preserving the factual substrate. Because PHD admits multiple valid outputs, HypoEval combines bidirectional pairwise judgments with Bradley--Terry--Davidson aggregation for ranking and six-dimensional rubric scoring for diagnosis. Experiments on 15 frontier LLMs reveal clear capability stratification and model-dependent effects of structured analytical skills, with gains for several lower-performing models on HypoArena but regressions for other systems, including a top-performing model. Compared with absolute rubric scoring, arena evaluation resolves finer-grained differences among models, with aggregated rankings showing strong agreement with human experts and an independent judge. Together, these results support treating PHD as a distinct target for evaluating how LLMs formulate investigative directions when final conclusions are withheld. Our code and data are publicly available at this http URL and this http URL.
Subjects:
Computation and Language (cs.CL)
Cite as: arXiv:2607.15766 [cs.CL]
(or arXiv:2607.15766v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2607.15766
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Tianyun Zhong [view email] [v1] Fri, 17 Jul 2026 08:56:43 UTC (2,460 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Before the Action: Benchmarking LLMs on Prospective Hypothesis Discovery, by Tianyun Zhong and 17 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CL
new | recent | 2026-07
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)