AwesomeLit: Towards Hypothesis Generation with Agent-Supported Literature Research

2026-03-23

AI Summary

This work addresses the challenges faced by novice researchers in identifying literature gaps within unfamiliar domains, where existing tools lack specificity and large language models suffer from opacity and hallucination. To overcome these limitations, the authors propose a human-AI collaborative, visual research agent system that employs a transparent, user-controllable agent workflow. The system dynamically constructs traceable query exploration trees to guide research pathways and integrates a semantic similarity view to reveal relationships among papers, enabling users to iteratively refine broad research intents into concrete hypotheses. Preliminary qualitative evaluation indicates that the system enhances users’ exploration efficiency, ability to discover viable research directions, and confidence in the reliability of generated insights.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Multiagent Systems: Agent-Based Simulation and Emergent Behavior

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search
• Economics, Online Markets and Human Computation: Research challenges in human and human-AI computation

Abstract

There are different goals for literature research, from understanding an unfamiliar topic to generate hypothesis for the next research project. The nature of literature research also varies according to user's familiarity level of the topic. For inexperienced researchers, identifying gaps in the existing literature and generating feasible hypothesis are crucial but challenging. While general ``deep research'' tools can be used, they are not designed for such use case, thus often not effective. In addition, the ``black box" nature and hallucination of Large Language Models (LLMs) often lead to distrust. In this paper, we introduce a human-agent collaborative visualization system AwesomeLit to address this need. It has several novel features: a transparent user-steerable agentic workflow; a dynamically generated query exploring tree, visualizing the exploration path and provenance; and a semantic similarity view, depicting the relationships between papers. It enables users to transition from general intentions to detailed research topics. Finally, a qualitative study involving several early researchers showed that AwesomeLit is effective in helping users explore unfamiliar topics, identify promising research directions, and improve confidence in research results.

Problem

• hypothesis generation
• literature research
• research gap identification
• early-career researchers
• LLM hallucination

Innovation

• human-agent collaboration
• literature-based hypothesis generation
• transparent agentic workflow
• query exploration tree
• semantic similarity visualization