[Submitted on 14 Aug 2026]
Title:DeepInstructor: An Agentic AI Instructor for Experience-Driven Idea Evaluation
View a PDF of the paper titled DeepInstructor: An Agentic AI Instructor for Experience-Driven Idea Evaluation, by Rongcan Pei and 9 other authors
View PDF HTML (experimental)
Abstract:As automated scientific discovery advances, Large Language Models (LLMs) can now generate research ideas at an unprecedented scale, shifting the bottleneck from idea generation to idea evaluation. Existing evaluators mainly rely on parametric LLM knowledge or unstructured retrieval, producing judgments that lack the experience-grounded reasoning used by human instructors. To address this, we propose DeepInstructor, an agentic framework that formulates idea evaluation as reasoning over structured scholarly experience. DeepInstructor constructs an Experience Graph from 58,607 peer reviews and employs a ReAct-based agent to retrieve dimension-specific evidence for traceable evaluation. We further introduce DeepInstruct, a dataset with controlled pairwise comparisons across novelty, significance, and feasibility. Experiments show that DeepInstructor substantially outperforms existing baselines, improving Hit@1 and Hit@2 alignment with human judgments by 24.4% and 29.7%, respectively. Our findings suggest that scientific idea evaluation can be grounded in explicit reasoning over structured scholarly experience
Subjects:
Computation and Language (cs.CL); Information Retrieval (cs.IR)
Cite as: arXiv:2609.22104 [cs.CL]
(or arXiv:2609.22104v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2609.22104
arXiv-issued DOI via DataCite
Submission history
From: Fang Guo [view email] [v1] Fri, 14 Aug 2026 01:52:00 UTC (1,468 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled DeepInstructor: An Agentic AI Instructor for Experience-Driven Idea Evaluation, by Rongcan Pei and 9 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CL
new | recent | 2026-09
Change to browse by:
cs cs.IR
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?)