S$^2$-MAD: Breaking the Token Barrier to Enhance Multi-Agent Debate Efficiency

• URL: http://arxiv.org/abs/2502.04790v1
• Date: Fri, 07 Feb 2025 09:49:56 GMT
• Title: S$^2$-MAD: Breaking the Token Barrier to Enhance Multi-Agent Debate Efficiency
• Authors: Yuting Zeng, Weizhe Huang, Lei Jiang, Tongxuan Liu, Xitai Jin, Chen Tianying Tiana, Jing Li, Xiaohua Xu,
• Abstract summary: Multi-agent Debate (MAD) has emerged as a viable approach for enhancing the reasoning capabilities of large language models (LLMs) We introduce a novel sparsification strategy designed to reduce token costs within MAD. This approach minimizes ineffective exchanges of information and unproductive discussions among agents, thereby enhancing the overall efficiency of the debate process.
• Score: 5.195584743414427
• License:
• Abstract: Large language models (LLMs) have demonstrated remarkable capabilities across various natural language processing (NLP) scenarios, but they still face challenges when handling complex arithmetic and logical reasoning tasks. While Chain-Of-Thought (CoT) reasoning, self-consistency (SC) and self-correction strategies have attempted to guide models in sequential, multi-step reasoning, Multi-agent Debate (MAD) has emerged as a viable approach for enhancing the reasoning capabilities of LLMs. By increasing both the number of agents and the frequency of debates, the performance of LLMs improves significantly. However, this strategy results in a significant increase in token costs, presenting a barrier to scalability. To address this challenge, we introduce a novel sparsification strategy designed to reduce token costs within MAD. This approach minimizes ineffective exchanges of information and unproductive discussions among agents, thereby enhancing the overall efficiency of the debate process. We conduct comparative experiments on multiple datasets across various models, demonstrating that our approach significantly reduces the token costs in MAD to a considerable extent. Specifically, compared to MAD, our approach achieves an impressive reduction of up to 94.5\% in token costs while maintaining performance degradation below 2.0\%.

Related papers

• Stepwise Perplexity-Guided Refinement for Efficient Chain-of-Thought Reasoning in Large Language Models [56.37421741507468]
  Chain-of-Thought (CoT) reasoning has significantly enhanced the performance of large language models (LLMs) We propose a method to identify critical reasoning steps using perplexity as a measure of their importance.
  arXiv  Detail & Related papers  (2025-02-18T20:04:51Z)
• DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs [70.91804882618243]
  This paper proposes DSMoE, a novel approach that achieves sparsification by partitioning pre-trained FFN layers into computational blocks. We implement adaptive expert routing using sigmoid activation and straight-through estimators, enabling tokens to flexibly access different aspects of model knowledge. Experiments on LLaMA models demonstrate that under equivalent computational constraints, DSMoE achieves superior performance compared to existing pruning and MoE approaches.
  arXiv  Detail & Related papers  (2025-02-18T02:37:26Z)
• Self-Regulation and Requesting Interventions [63.5863047447313]
  We propose an offline framework that trains a "helper" policy to request interventions. We score optimal intervention timing with PRMs and train the helper model on these labeled trajectories. This offline approach significantly reduces costly intervention calls during training.
  arXiv  Detail & Related papers  (2025-02-07T00:06:17Z)
• Learning Free Token Reduction for Multi-Modal LLM [3.4026156483879517]
  Vision-Language Models (VLMs) have achieved remarkable success across a range of multimodal tasks. However, their practical deployment is often constrained by high computational costs and prolonged inference times. We propose a token compression paradigm that operates on both spatial and temporal dimensions.
  arXiv  Detail & Related papers  (2025-01-29T02:52:32Z)
• Token-Budget-Aware LLM Reasoning [33.81357562939748]
  Chain-of-Thought (CoT) reasoning incurs significant overhead in token usage. We propose a token-budget-aware LLM reasoning framework. Our method effectively reduces token costs in CoT reasoning with only a slight performance reduction.
  arXiv  Detail & Related papers  (2024-12-24T16:55:45Z)
• Less is More: A Simple yet Effective Token Reduction Method for Efficient Multi-modal LLMs [14.533229831531168]
  We introduce a new approach, Token Reduction using CLIP Metric (TRIM), aimed at improving the efficiency of MLLMs without sacrificing their performance. Inspired by human attention patterns in Visual Question Answering (VQA) tasks, TRIM presents a fresh perspective on the selection and reduction of image tokens. The results demonstrate a significant reduction in computational overhead while maintaining a consistent level of performance.
  arXiv  Detail & Related papers  (2024-09-17T08:56:27Z)
• Strategic Chain-of-Thought: Guiding Accurate Reasoning in LLMs through Strategy Elicitation [16.350747493026432]
  The Chain-of-Thought (CoT) paradigm has emerged as a critical approach for enhancing the reasoning capabilities of large language models (LLMs) We propose the textbfStrategic Chain-of-Thought (SCoT) to refine LLM performance by integrating strategic knowledge prior to generating intermediate reasoning steps. SCoT employs a two-stage approach within a single prompt: first eliciting an effective problem-solving strategy, which is then used to guide the generation of high-quality CoT paths and final answers.
  arXiv  Detail & Related papers  (2024-09-05T06:28:05Z)
• STBA: Towards Evaluating the Robustness of DNNs for Query-Limited Black-box Scenario [50.37501379058119]
  We propose the Spatial Transform Black-box Attack (STBA) to craft formidable adversarial examples in the query-limited scenario. We show that STBA could effectively improve the imperceptibility of the adversarial examples and remarkably boost the attack success rate under query-limited settings.
  arXiv  Detail & Related papers  (2024-03-30T13:28:53Z)
• Exploiting Activation Sparsity with Dense to Dynamic-k Mixture-of-Experts Conversion [4.716845031095804]
  Transformer models can face practical limitations due to their high computational requirements. Such models exhibit significant activation sparsity, which can be leveraged to reduce the inference cost by converting parts of the network into equivalent Mixture-of-Experts (MoE) layers. We demonstrate that the efficiency of the conversion can be significantly enhanced by a proper regularization of the activation sparsity of the base model.
  arXiv  Detail & Related papers  (2023-10-06T16:34:51Z)
• OverPrompt: Enhancing ChatGPT through Efficient In-Context Learning [49.38867353135258]
  We propose OverPrompt, leveraging the in-context learning capability of LLMs to handle multiple task inputs. Our experiments show that OverPrompt can achieve cost-efficient zero-shot classification without causing significant detriment to task performance.
  arXiv  Detail & Related papers  (2023-05-24T10:08:04Z)
• Enhancing Chain-of-Thoughts Prompting with Iterative Bootstrapping in Large Language Models [81.01397924280612]
  Large language models (LLMs) can achieve highly effective performance on various reasoning tasks by incorporating step-by-step chain-of-thought (CoT) prompting as demonstrations. We introduce Iter-CoT (Iterative bootstrapping in Chain-of-Thoughts Prompting), an iterative bootstrapping approach for selecting exemplars and generating reasoning chains.
  arXiv  Detail & Related papers  (2023-04-23T13:54:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.