# Perspectra: Choosing Your Experts Enhances Critical Thinking in Multi-Agent Research Ideation

arXiv: https://arxiv.org/abs/2509.20553 · HTML: https://mlsanity.com/paper/2509.20553/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 30 of its 93 references that are in the map.
- First posted on arXiv 24 Sep 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 30 of 30)

- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [Large Language Model based Multi-Agents: A Survey of Progress and Challenges](https://mlsanity.com/paper/2402.01680/) (2024)
- [Scaling Synthetic Data Creation with 1,000,000,000 Personas](https://mlsanity.com/paper/2406.20094/) (2024)
- [LightRAG: Simple and Fast Retrieval-Augmented Generation](https://mlsanity.com/paper/2410.05779/) (2024)
- [DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments](https://mlsanity.com/paper/2504.03160/) (2025)
- [Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks](https://mlsanity.com/paper/2411.04468/) (2024)
- [ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Models](https://mlsanity.com/paper/2404.07738/) (2024)
- [Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems](https://mlsanity.com/paper/2505.00212/) (2025)
- [OpenAlex: A fully-open index of scholarly works, authors, venues, institutions, and concepts](https://mlsanity.com/paper/2205.01833/) (2022)
- [Deep Research Agents: A Systematic Examination And Roadmap](https://mlsanity.com/paper/2506.18096/) (2025)
- [Simulating Classroom Education with LLM-Empowered Agents](https://mlsanity.com/paper/2406.19226/) (2024)
- [A Survey of Context Engineering for Large Language Models](https://mlsanity.com/paper/2507.13334/) (2025)
- [G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems](https://mlsanity.com/paper/2506.07398/) (2025)
- [The Semantic Scholar Open Data Platform](https://mlsanity.com/paper/2301.10140/) (2023)
- [InternAgent: When Agent Becomes the Scientist -- Building Closed-Loop System from Hypothesis to Verification](https://mlsanity.com/paper/2505.16938/) (2025)
- [Into the Unknown Unknowns: Engaged Human Learning through Participation in Language Model Agent Conversations](https://mlsanity.com/paper/2408.15232/) (2024)
- [Human-LLM Compound System for Scientific Ideation through Facet Recombination and Novelty Evaluation](https://mlsanity.com/paper/2409.14634/) (2024)
- [MDTeamGPT: A Self-Evolving LLM-based Multi-Agent Framework for Multi-Disciplinary Team Medical Consultation](https://mlsanity.com/paper/2503.13856/) (2025)
- [IRIS: Interactive Research Ideation System for Accelerating Scientific Discovery](https://mlsanity.com/paper/2504.16728/) (2025)
- [Argumentative Experience: Reducing Confirmation Bias on Controversial Issues through LLM-Generated Multi-Persona Debates](https://mlsanity.com/paper/2412.04629/) (2024)
- [SocraSynth: Multi-LLM Reasoning with Conditional Statistics](https://mlsanity.com/paper/2402.06634/) (2024)
- [DBox: Scaffolding Algorithmic Programming Learning through Learner-LLM Co-Decomposition](https://mlsanity.com/paper/2502.19133/) (2025)
- [From Conversation to Orchestration: HCI Challenges and Opportunities in Interactive Multi-Agentic Systems](https://mlsanity.com/paper/2506.20091/) (2025)
- [Conversational Agents as Catalysts for Critical Thinking: Challenging Design Fixation in Group Design](https://mlsanity.com/paper/2406.11125/) (2024)
- [Conversational Agents as Catalysts for Critical Thinking: Challenging Social Influence in Group Decision-making](https://mlsanity.com/paper/2503.14263/) (2025)
- [From Consumption to Collaboration: Measuring Interaction Patterns to Augment Human Cognition in Open-Ended Tasks](https://mlsanity.com/paper/2504.02780/) (2025)
- [Large Language Model-Empowered Interactive Load Forecasting](https://mlsanity.com/paper/2505.16577/) (2025)
- [Scaffolding Recursive Divergence and Convergence in Story Ideation](https://mlsanity.com/paper/2507.03307/) (2025)
- [Fostering User Engagement in the Critical Reflection of Arguments](https://mlsanity.com/paper/2308.09061/) (2023)
- [MetaCrit: A Critical Thinking Framework for Self-Regulated LLM Reasoning](https://mlsanity.com/paper/2507.15015/) (2025)

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

- [ScholarEval: Research Idea Evaluation Grounded in Literature](https://mlsanity.com/paper/2510.16234/) (2025)
- [AgentPanel: Toward a New Paradigm for Human--AI Collaboration in Exploring Scientific Questions](https://mlsanity.com/paper/2608.03283/) (2026)
- [Designing Proactive Thought Partners for Writing](https://mlsanity.com/paper/2609.01588/) (2026)
- [DocuTeam: Mixed-Initiative Multi-Agent Discussions around Evolving Documents](https://mlsanity.com/paper/2609.29309/) (2026)

## Abstract (arXiv)

Recent advances in multi-agent systems (MAS) enable tools for information search and ideation by assigning personas to agents. However, how users can effectively control, steer, and critically evaluate collaboration among multiple domain-expert agents remains underexplored. We present Perspectra, an interactive MAS that visualizes and structures deliberation among LLM agents via a forum-style interface, supporting @-mention to invite targeted agents, threading for parallel exploration, with a real-time mind map for visualizing arguments and rationales. In a within-subjects study with 18 participants, we compared Perspectra to a group-chat baseline as they developed research proposals. Our findings show that Perspectra significantly increased the frequency and depth of critical-thinking behaviors, elicited more interdisciplinary replies, and led to more frequent proposal revisions than the group chat condition. We discuss implications for designing multi-agent tools that scaffold critical thinking by supporting user control over multi-agent adversarial discourse.