# Group Think: Multiple Concurrent Reasoning Agents Collaborating at Token Level Granularity

arXiv: https://arxiv.org/abs/2505.11107 · HTML: https://mlsanity.com/paper/2505.11107/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning.
- Builds on 16 of its 40 references that are in the map.
- First posted on arXiv 16 May 2025.

## Placed in

- LLM reasoning / [Test-time compute and efficient thinking](https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/)
- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 16 of 16)

- [Large Language Monkeys: Scaling Inference Compute with Repeated Sampling](https://mlsanity.com/paper/2407.21787/) (2024)
- [Large Language Models: A Survey](https://mlsanity.com/paper/2402.06196/) (2024)
- [Mixture-of-Agents Enhances Large Language Model Capabilities](https://mlsanity.com/paper/2406.04692/) (2024)
- [Multi-Agent Collaboration Mechanisms: A Survey of LLMs](https://mlsanity.com/paper/2501.06322/) (2025)
- [A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?](https://mlsanity.com/paper/2503.24235/) (2025)
- [Large Language Model Guided Tree-of-Thought](https://mlsanity.com/paper/2305.08291/) (2023)
- [Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions](https://mlsanity.com/paper/2411.14405/) (2024)
- [Cumulative Reasoning with Large Language Models](https://mlsanity.com/paper/2308.04371/) (2023)
- [Learning Adaptive Parallel Reasoning with Language Models](https://mlsanity.com/paper/2504.15466/) (2025)
- [Towards Reasoning in Large Language Models via Multi-Agent Peer Review Collaboration](https://mlsanity.com/paper/2311.08152/) (2023)
- [Sample, Scrutinize and Scale: Effective Inference-Time Search by Scaling Verification](https://mlsanity.com/paper/2502.01839/) (2025)
- [When To Solve, When To Verify: Compute-Optimal Problem Solving and Generative Verification for LLM Reasoning](https://mlsanity.com/paper/2504.01005/) (2025)
- [A Survey of Test-Time Compute: From Intuitive Inference to Deliberate Reasoning](https://mlsanity.com/paper/2501.02497/) (2025)
- [Hogwild! Inference: Parallel LLM Generation via Concurrent Attention](https://mlsanity.com/paper/2504.06261/) (2025)
- [When One LLM Drools, Multi-LLM Collaboration Rules](https://mlsanity.com/paper/2502.04506/) (2025)
- [Learning to Keep a Promise: Scaling Language Model Decoding Parallelism with Learned Asynchronous Decoding](https://mlsanity.com/paper/2502.11517/) (2025)

## Built on by (most cited first, 22 of 22)

- [Parallel-R1: Towards Parallel Thinking via Reinforcement Learning](https://mlsanity.com/paper/2509.07980/) (2025)
- [Parallel-Probe: Towards Efficient Parallel Thinking via 2D Probing](https://mlsanity.com/paper/2602.03845/) (2026)
- [ASPD: Unlocking Adaptive Serial-Parallel Decoding by Exploring Intrinsic Parallelism in LLMs](https://mlsanity.com/paper/2508.08895/) (2025)
- [A Survey on Parallel Reasoning](https://mlsanity.com/paper/2510.12164/) (2025)
- [iMAD: Intelligent Multi-Agent Debate for Efficient and Accurate LLM Inference](https://mlsanity.com/paper/2511.11306/) (2025)
- [Benefits and Limitations of Communication in Multi-Agent Reasoning](https://mlsanity.com/paper/2510.13903/) (2025)
- [The Era of Agentic Organization: Learning to Organize with Language Models](https://mlsanity.com/paper/2510.26658/) (2025)
- [Asynchronous Reasoning: Training-Free Interactive Thinking LLMs](https://mlsanity.com/paper/2512.10931/) (2025)
- [Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models](https://mlsanity.com/paper/2605.17672/) (2026)
- [Generalized Parallel Scaling with Interdependent Generations](https://mlsanity.com/paper/2510.01143/) (2025)
- [Multi-Stream LLMs: Unblocking Language Models with Parallel Streams of Thoughts, Inputs and Outputs](https://mlsanity.com/paper/2605.12460/) (2026)
- [Towards Ethical Multi-Agent Systems of Large Language Models: A Mechanistic Interpretability Perspective](https://mlsanity.com/paper/2512.04691/) (2025)
- [One-Token Verification for Reasoning Correctness Estimation](https://mlsanity.com/paper/2603.01025/) (2026)
- [LaneRoPE: Positional Encoding for Collaborative Parallel Reasoning and Generation](https://mlsanity.com/paper/2605.27570/) (2026)
- [A Note on Code Quality Score: LLMs for Maintainable Large Codebases](https://mlsanity.com/paper/2508.02732/) (2025)
- [Parallel Decoder Transformer: Planner-Conditioned Latent Coordination for Model-Intrinsic Parallel Generation](https://mlsanity.com/paper/2512.10054/) (2025)
- [Emergence: Overcoming Privileged Information Bias in Asymmetric Embodied Agents via Active Querying](https://mlsanity.com/paper/2512.15776/) (2025)
- [Efficient Reasoning on the Edge](https://mlsanity.com/paper/2603.16867/) (2026)
- [LACE: Lattice Attention for Cross-thread Exploration](https://mlsanity.com/paper/2604.15529/) (2026)
- [Streaming Communication in Multi-Agent Reasoning](https://mlsanity.com/paper/2606.05158/) (2026)
- [Second Thought: Reasoning in Parallel as LLM Agents Act and Observe](https://mlsanity.com/paper/2608.13667/) (2026)
- [Line-Coupled Language Model](https://mlsanity.com/paper/2609.07129/) (2026)

## Abstract (arXiv)

Recent advances in large language models (LLMs) have demonstrated the power of reasoning through self-generated chains of thought. Multiple reasoning agents can collaborate to raise joint reasoning quality above individual outcomes. However, such agents typically interact in a turn-based manner, trading increased latency for improved quality. In this paper, we propose Group Think--a single LLM that acts as multiple concurrent reasoning agents, or thinkers. With shared visibility into each other's partial generation progress, Group Think introduces a new concurrent-reasoning paradigm in which multiple reasoning trajectories adapt dynamically to one another at the token level. For example, a reasoning thread may shift its generation mid-sentence upon detecting that another thread is better positioned to continue. This fine-grained, token-level collaboration enables Group Think to reduce redundant reasoning and improve quality while achieving significantly lower latency. Moreover, its concurrent nature allows for efficient utilization of idle computational resources, making it especially suitable for edge inference, where very small batch size often underutilizes local~GPUs. We give a simple and generalizable modification that enables any existing LLM to perform Group Think on a local GPU. We also present an evaluation strategy to benchmark reasoning latency and empirically demonstrate latency improvements using open-source LLMs that were not explicitly trained for Group Think. We hope this work paves the way for future LLMs to exhibit more sophisticated and more efficient collaborative behavior for higher quality generation.