Evolving Roles of LLMs in Scientific Innovation: Assistant, Collaborator, Scientist, and Evaluator

TL;DR

This survey introduces a four-role framework for understanding LLMs in scientific innovation, analyzing their capabilities, limitations, and human oversight needs across roles like Assistant, Collaborator, Scientist, and Evaluator.

Contribution

It proposes a novel four-role framework integrating autonomy, cognition, and innovation dimensions to distinguish research support from discovery in LLM applications.

Findings

Assistant systems are mature in retrieval and synthesis but unreliable in open-ended tasks.

Collaborator systems expand hypothesis space but face novelty-grounding challenges.

Scientist systems automate workflows but encounter reliability and safety issues.

Abstract

Large language models (LLMs) are increasingly used in scientific research and discovery, supporting tasks ranging from literature retrieval and synthesis to hypothesis generation, autonomous experimentation, and research evaluation. Existing surveys often conflate scientific research with scientific discovery and typically organize systems by domain, task, or autonomy level alone. In this survey, we propose a four-role framework for understanding LLMs in scientific innovation: Assistant, Collaborator, Scientist, and Evaluator. The framework integrates three complementary dimensions: autonomy level, cognitive function, and scientific innovation, to distinguish research-oriented support from frontier-oriented discovery. We review representative methods, benchmarks, and evaluation practices for each role, examining their capabilities, limitations, and human oversight requirements. Across the literature, Assistant systems are comparatively mature in retrieval and synthesis but remain unreliable in open-ended applications; Collaborator systems expand the space of candidate hypotheses yet struggle with novelty-grounding trade-offs; Scientist systems increasingly automate research workflows but face reliability and safety bottlenecks; and Evaluator systems support review and verification while remaining weak in novelty assessment. We argue that progress in AI for science depends not only on model capability, but also on evaluation, oversight, accountability, and institutional integration.