# Before the Action: Benchmarking LLMs on Prospective Hypothesis Discovery

arXiv: https://arxiv.org/abs/2607.15766 · HTML: https://mlsanity.com/paper/2607.15766/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 22 references that are in the map.
- First posted on arXiv 17 Jul 2026.

## Builds on (most cited first, 14 of 14)

- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers](https://mlsanity.com/paper/2409.04109/) (2024)
- [DSBench: How Far Are Data Science Agents from Becoming Data Science Experts?](https://mlsanity.com/paper/2409.07703/) (2024)
- [DiscoveryBench: Towards Data-Driven Discovery with Large Language Models](https://mlsanity.com/paper/2407.01725/) (2024)
- [Kosmos: An AI Scientist for Autonomous Discovery](https://mlsanity.com/paper/2511.02824/) (2025)
- [DABstep: Data Agent Benchmark for Multi-step Reasoning](https://mlsanity.com/paper/2506.23719/) (2025)
- [HypoBench: Towards Systematic and Principled Benchmarking for Hypothesis Generation](https://mlsanity.com/paper/2504.11524/) (2025)
- [InsightBench: Evaluating Business Analytics Agents Through Multi-Step Insight Generation](https://mlsanity.com/paper/2407.06423/) (2024)
- [Literature Meets Data: A Synergistic Approach to Hypothesis Generation](https://mlsanity.com/paper/2410.17309/) (2024)
- [SciArena: An Open Evaluation Platform for Non-Verifiable Scientific Literature-Grounded Tasks](https://mlsanity.com/paper/2507.01001/) (2025)
- [GraphEval: A Lightweight Graph-Based LLM Framework for Idea Evaluation](https://mlsanity.com/paper/2503.12600/) (2025)
- [HypER: Literature-grounded Hypothesis Generation and Distillation with Provenance](https://mlsanity.com/paper/2506.12937/) (2025)
- [Toward Reliable Scientific Hypothesis Generation: Evaluating Truthfulness and Hallucination in Large Language Models](https://mlsanity.com/paper/2505.14599/) (2025)
- [InnoEval: On Research Idea Evaluation as a Knowledge-Grounded, Multi-Perspective Reasoning Problem](https://mlsanity.com/paper/2602.14367/) (2026)

## Built on by (most cited first, 1 of 1)

- [ULTRADISCOVERY: Abductive Exploration in an Interconnected, Epistemically Open Universe](https://mlsanity.com/paper/2610.03092/) (2026)

## Abstract (arXiv)

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 github.com/SKYLENAGE-AI/HypoArena and github.com/SKYLENAGE-AI/HypoArena.