Autonomous Scientific Discovery via Iterative Meta-Reflection

Hugging Face Daily Papers Papers
autonomous-scientific-discovery meta-reflection llm statistical-testing multimodal hypothesis-generation open-ended-research

Summary

DiscoPER is an autonomous framework leveraging large language models and dynamic code generation for open-ended scientific research, using second-order meta-reflection to synthesize discoveries and statistical testing for rigor. Evaluated on a multimodal ecological benchmark, it outperforms baselines in recovering known patterns.

Autonomous scientific discovery systems offer the potential to accelerate research by automating the process of hypothesis generation and validation. However, current systems operate within constrained search spaces or require predefined research questions, limiting their capacity for true open-ended inquiry. Furthermore, while they generate hypotheses iteratively, they largely lack the ability to explicitly synthesize their own accumulated findings to uncover complex, interconnected phenomena. We introduce DiscoPER, an autonomous large language model-powered framework that conducts open-ended research by dynamically generating and executing code to explore datasets without pre-specified research objectives. To ensure rigorous scientific validity, every proposed discovery must pass statistical testing. To overcome the limitations of isolated search, our framework introduces a second-order reasoning mechanism that periodically analyzes its own accumulated discoveries. By treating prior discoveries as empirical data, DiscoPER identifies structural patterns, confounds, and epistemic gaps, actively redirecting hypothesis exploration toward uncharted regions of the search space. The search space is further expanded by incorporating tool use, enabling the system to explore hypotheses beyond structured metadata by seamlessly processing and extracting useful information from multimodal sources like images. Evaluated on iNatDisco, a new multimodal ecological knowledge benchmark with pattern-level ground truth obtained from peer-reviewed literature, DiscoPER recovers 8 of 9 known patterns with a 72.7% hypothesis support rate, outperforming both classical causal discovery and LLM-guided baselines. Ablations show that DiscoPER scales with more data, and confirms the benefits of second-order meta-reflection.
Original Article
View Cached Full Text

Cached at: 07/02/26, 03:46 AM

Paper page - Autonomous Scientific Discovery via Iterative Meta-Reflection

Source: https://huggingface.co/papers/2607.01131

Abstract

An autonomous scientific discovery framework uses large language models and dynamic code generation to conduct open-ended research while maintaining statistical rigor through meta-reflection and multimodal data processing.

Autonomous scientific discoverysystems offer the potential to accelerate research by automating the process ofhypothesis generationand validation. However, current systems operate within constrained search spaces or require predefined research questions, limiting their capacity for true open-ended inquiry. Furthermore, while they generate hypotheses iteratively, they largely lack the ability to explicitly synthesize their own accumulated findings to uncover complex, interconnected phenomena. We introduce DiscoPER, an autonomouslarge language model-powered frameworkthat conducts open-ended research by dynamically generating and executing code to explore datasets without pre-specified research objectives. To ensure rigorous scientific validity, every proposed discovery must passstatistical testing. To overcome the limitations of isolated search, our framework introduces asecond-order reasoningmechanism that periodically analyzes its own accumulated discoveries. By treating prior discoveries as empirical data, DiscoPER identifies structural patterns, confounds, and epistemic gaps, actively redirecting hypothesis exploration toward uncharted regions of the search space. The search space is further expanded by incorporating tool use, enabling the system to explore hypotheses beyond structured metadata by seamlessly processing and extracting useful information frommultimodal sourceslike images. Evaluated oniNatDisco, a new multimodal ecological knowledge benchmark withpattern-level ground truthobtained from peer-reviewed literature, DiscoPER recovers 8 of 9 known patterns with a 72.7% hypothesis support rate, outperforming both classicalcausal discoveryandLLM-guided baselines. Ablations show that DiscoPER scales with more data, and confirms the benefits of second-ordermeta-reflection.

View arXiv pageView PDFAdd to collection

Get this paper in your agent:

hf papers read 2607\.01131

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2607.01131 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2607.01131 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2607.01131 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Scaling Scientific Discovery Environments for Turn-Level Agentic RL

arXiv cs.AI

This paper introduces SciDisco, a scalable framework for training scientific discovery agents via process-verifiable environments, DAG-grounded trajectory synthesis, and turn-level reinforcement learning. The proposed SciDisco-14B model achieves state-of-the-art on hypothesis-driven scientific data analysis benchmarks.

Disco-RAG: Discourse-Aware Retrieval-Augmented Generation

arXiv cs.CL

Disco-RAG proposes a discourse-aware retrieval-augmented generation framework that integrates discourse signals through intra-chunk discourse trees and inter-chunk rhetorical graphs to improve knowledge synthesis in LLMs. The method achieves state-of-the-art results on QA and summarization benchmarks without fine-tuning.

An Interactive Paradigm for Deep Research

arXiv cs.CL

SteER is a framework for steerable deep research that introduces mid-process, interpretable control via adaptive pause decisions and live persona modeling, outperforming baselines by up to 22.80% on alignment and preferred by human readers in over 85% of pairwise alignment judgments.