# AgentPanel: Toward a New Paradigm for Human--AI Collaboration in Exploring Scientific Questions

arXiv: https://arxiv.org/abs/2608.03283 · HTML: https://mlsanity.com/paper/2608.03283/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 30 references that are in the map.
- First posted on arXiv 4 Aug 2026.

## Builds on (most cited first, 22 of 22)

- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate](https://mlsanity.com/paper/2308.07201/) (2023)
- [Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers](https://mlsanity.com/paper/2409.04109/) (2024)
- [ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Models](https://mlsanity.com/paper/2404.07738/) (2024)
- [The Ideation-Execution Gap: Execution Outcomes of LLM-Generated versus Human Research Ideas](https://mlsanity.com/paper/2506.20803/) (2025)
- [Stop Overvaluing Multi-Agent Debate -- We Must Rethink Evaluation and Embrace Model Heterogeneity](https://mlsanity.com/paper/2502.08788/) (2025)
- [AI Idea Bench 2025: AI Research Idea Generation Benchmark](https://mlsanity.com/paper/2504.14191/) (2025)
- [The Avengers: A Simple Recipe for Uniting Smaller Language Models to Challenge Proprietary Giants](https://mlsanity.com/paper/2505.19797/) (2025)
- [Evaluating LLMs' Divergent Thinking Capabilities for Scientific Idea Generation with Minimal Context](https://mlsanity.com/paper/2412.17596/) (2024)
- [Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence](https://mlsanity.com/paper/2410.11163/) (2024)
- [HindSight: Evaluating LLM-Generated Research Ideas via Future Impact](https://mlsanity.com/paper/2603.15164/) (2026)
- [Autonomous Agents Coordinating Distributed Discovery Through Emergent Artifact Exchange](https://mlsanity.com/paper/2603.14312/) (2026)
- [A Review of LLM-Assisted Ideation](https://mlsanity.com/paper/2503.00946/) (2025)
- [Towards AI as Colleagues: Multi-Agent System Improves Structured Ideation Processes](https://mlsanity.com/paper/2510.23904/) (2025)
- [PerPilot: Personalizing VLM-based Mobile Agents via Memory and Exploration](https://mlsanity.com/paper/2508.18040/) (2025)
- [Perspectra: Choosing Your Experts Enhances Critical Thinking in Multi-Agent Research Ideation](https://mlsanity.com/paper/2509.20553/) (2025)
- [Idea2Plan: Exploring AI-Powered Research Planning](https://mlsanity.com/paper/2510.24891/) (2025)
- [Design First, Code Later: Aesthetically Pleasing Template-Free Slides Generation](https://mlsanity.com/paper/2605.26451/) (2026)
- [Understanding Human-Multi-Agent Team Formation for Creative Work](https://mlsanity.com/paper/2601.13865/) (2026)

## Built on by (most cited first, 1 of 1)

- [RSI-Router: Evolving Subtask-Level LLM Routing and Skills for Cost-Efficient Agents](https://mlsanity.com/paper/2609.34712/) (2026)

## Abstract (arXiv)

Identifying promising scientific ideas remains an important challenge in research practice. Researchers commonly rely on small-group discussions or one-to-one interactions with a single large language model, yet these approaches often expose them to only a limited range of perspectives and directions. We present AgentPanel, a multi-agent forum for human--AI collaboration in scientific exploration. Heterogeneous agents asynchronously discuss scientific questions in a forum-style environment, while researchers can submit questions, browse and organize candidate ideas, engage agents in follow-up interactions, and optionally generate post-hoc summary reports. We evaluate AgentPanel in terms of idea quality, exploration breadth, interaction effectiveness, candidate-selection efficiency, and practical utility. Offline experiments show that AgentPanel outperforms a centralized multi-agent debate baseline. A human study with 20 participants further shows that users value AgentPanel for perspective diversity and exploration support. In experience-based comparisons with commonly used LLM tools, 65% of participants favored AgentPanel for both breadth of research directions and overall suitability for early-stage exploration. The platform is publicly available at https://agentpanel.cc/.