# WisPaper: Your AI Scholar Search Engine

arXiv: https://arxiv.org/abs/2512.06879 · HTML: https://mlsanity.com/paper/2512.06879/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 20 references that are in the map.
- First posted on arXiv 7 Dec 2025.

## Builds on (most cited first, 12 of 12)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [ChemCrow: Augmenting large-language models with chemistry tools](https://mlsanity.com/paper/2304.05376/) (2023)
- [Agent Laboratory: Using LLM Agents as Research Assistants](https://mlsanity.com/paper/2501.04227/) (2025)
- [Query Rewriting for Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2305.14283/) (2023)
- [ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Models](https://mlsanity.com/paper/2404.07738/) (2024)
- [Growth rates of modern science: A latent piecewise growth curve approach to model publication numbers from established and new literature databases](https://mlsanity.com/paper/2012.07675/) (2020)
- [PaSa: An LLM Agent for Comprehensive Academic Paper Search](https://mlsanity.com/paper/2501.10120/) (2025)
- [Large Language Model based Long-tail Query Rewriting in Taobao Search](https://mlsanity.com/paper/2311.03758/) (2023)
- [Query Expansion by Prompting Large Language Models](https://mlsanity.com/paper/2305.03653/) (2023)
- [LitSearch: A Retrieval Benchmark for Scientific Literature Search](https://mlsanity.com/paper/2407.18940/) (2024)
- [ResearchArena: Benchmarking Large Language Models' Ability to Collect and Organize Information as Research Agents](https://mlsanity.com/paper/2406.10291/) (2024)
- [Can Generative LLMs Create Query Variants for Test Collections? An Exploratory Study](https://mlsanity.com/paper/2501.17981/) (2025)

## Built on by (most cited first, 4 of 4)

- [InnoEval: On Research Idea Evaluation as a Knowledge-Grounded, Multi-Perspective Reasoning Problem](https://mlsanity.com/paper/2602.14367/) (2026)
- [ScholarGym: Benchmarking Large Language Model Capabilities in the Information-Gathering Stage of Deep Research](https://mlsanity.com/paper/2601.21654/) (2026)
- [Faithfulness-QA: A Counterfactual Entity Substitution Dataset for Training Context-Faithful RAG Models](https://mlsanity.com/paper/2604.25313/) (2026)
- [World Potential Model: Pretrained World Knowledge as Progress Potentials](https://mlsanity.com/paper/2610.09560/) (2026)

## Abstract (arXiv)

We present textscWisPaper, an end-to-end agent system that transforms how researchers discover, organize, and track academic literature. The system addresses two fundamental challenges. (1)~textitSemantic search limitations: existing academic search engines match keywords but cannot verify whether papers truly address complex research questions; and (2)~textitWorkflow fragmentation: researchers must manually stitch together separate tools for discovery, organization, and monitoring. textscWisPaper tackles these through three integrated modules. Scholar Search combines rapid keyword retrieval with textitDeep Search, in which an agentic model, textscWisModel, validates candidate papers against user queries through structured reasoning. Discovered papers flow seamlessly into Library with one click, where systematic organization progressively builds a user profile that sharpens the recommendations of AI Feeds, which continuously surfaces relevant new publications and in turn guides subsequent exploration, closing the loop from discovery to long-term awareness. On TaxoBench, textscWisPaper achieves 22.26% recall, surpassing the O3 baseline (20.92%). Furthermore, textscWisModel attains 93.70% validation accuracy, effectively mitigating retrieval hallucinations.