When Less is Enough: Efficient Inference via Collaborative Reasoning

• URL: http://arxiv.org/abs/2605.01111v1
• Date: Fri, 01 May 2026 21:31:59 GMT
• Title: When Less is Enough: Efficient Inference via Collaborative Reasoning
• Abstract summary: DUET is a collaborative inference framework in which a capable model and a lightweight model work together to solve a task.<n>As a result, DUET maintains strong reasoning performance with substantially lower inference cost than end-to-end inference using a large model alone.
• Score: 39.24624228580671
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: In this work, we introduce DUET (Dual-model Efficient Two-stage inference), a collaborative inference framework in which a capable model and a lightweight model work together to solve a task. Relying on a single large model to perform end-to-end reasoning and prediction often incurs substantial inference cost. In contrast, DUET decomposes inference into two stages: the capable model produces a reasoning signal, and the lightweight model interprets this signal to generate the final answer, allowing reasoning-intensive computation to be handled by the capable model while non-reasoning-intensive components are delegated to the lightweight model without sacrificing task performance. To achieve this objective, we propose a length-penalized joint training objective that encourages the capable model to transmit only the information that is sufficient for the lightweight model to solve the task. As a result, DUET maintains strong reasoning performance with substantially lower inference cost than end-to-end inference using a large model alone, saving up to 60% of the large model's output tokens on challenging reasoning benchmarks, including AIME and GPQA.

Related papers

• Before Thinking, Learn to Decide: Proactive Routing for Efficient Visual Reasoning [87.18590662029432]
  We propose PRP, a Proactive Routing Paradigm that enables early decision-making by jointly evaluating the competence of both the draft and target models.<n>Our draft Rating Learning (DRL) equips the draft model with an internal confidence estimator, while Joint Rating Learning (JRL) predicts how well the target model can handle a given query.<n>These ratings enable fine-grained, instance-level textbfProactive Routing and substantially accelerate inference without compromising overall performance.
  arXiv  Detail & Related papers  (2026-06-29T12:30:24Z)
• GlimpRouter: Efficient Collaborative Inference by Glimpsing One Token of Thoughts [10.808072653940263]
  Collaborative inference offers a promising solution by selectively allocating work between lightweight and large models.<n>We propose a novel perspective on step-wise collaboration: the difficulty of a reasoning step can be inferred from its very first token.<n>Glimp employs a lightweight model to generate only the first token of each reasoning step and routes the step to a larger model only when the initial token entropy exceeds a threshold.
  arXiv  Detail & Related papers  (2026-01-08T16:58:07Z)
• A2R: An Asymmetric Two-Stage Reasoning Framework for Parallel Reasoning [57.727084580884075]
  Asymmetric Two-Stage Reasoning framework designed to bridge gap between a model's potential and its actual performance.<n>A2R-Efficient is a "small-to-big" variant that combines a Qwen3-4B explorer with a Qwen3-8B synthesizer.<n>Results show A2R is not only a performance-boosting framework but also an efficient and practical solution for real-world applications.
  arXiv  Detail & Related papers  (2025-09-26T08:27:03Z)
• Don't Overthink It: A Survey of Efficient R1-style Large Reasoning Models [49.598776427454176]
  Large Reasoning Models (LRMs) have gradually become a research hotspot due to their outstanding performance in handling complex tasks.<n>However, with the widespread application of these models, the problem of overthinking has gradually emerged.<n>Various efficient reasoning methods have been proposed, aiming to reduce the length of reasoning paths without compromising model performance and reasoning capability.
  arXiv  Detail & Related papers  (2025-08-04T06:54:31Z)
• Mitigating Parameter Interference in Model Merging via Sharpness-Aware Fine-Tuning [6.110846759317336]
  Large-scale deep learning models with a pretraining-finetuning paradigm have led to a surge of numerous task-specific models fine-tuned from a common pre-trained model.<n>Research efforts have been made on merging these large models into a single multi-task model, particularly with simple arithmetic on parameters.<n>Such merging methodology faces a central challenge: interference between model parameters fine-tuned on different tasks.<n>We propose to fine-tune pre-trained models via sharpness-aware minimization.
  arXiv  Detail & Related papers  (2025-04-20T15:57:12Z)
• Training Language Models to Reason Efficiently [12.689316164465472]
  We use reinforcement learning to train large reasoning models to reason efficiently.<n>Our method incentivizes models to minimize unnecessary computational overhead while maintaining accuracy.<n> Experiments on two open-weight large reasoning models demonstrate significant reductions in inference cost while preserving most of the accuracy.
  arXiv  Detail & Related papers  (2025-02-06T19:18:16Z)
• DQ-BART: Efficient Sequence-to-Sequence Model via Joint Distillation and Quantization [75.72231742114951]
  Large-scale pre-trained sequence-to-sequence models like BART and T5 achieve state-of-the-art performance on many generative NLP tasks. These models pose a great challenge in resource-constrained scenarios owing to their large memory requirements and high latency. We propose to jointly distill and quantize the model, where knowledge is transferred from the full-precision teacher model to the quantized and distilled low-precision student model.
  arXiv  Detail & Related papers  (2022-03-21T18:04:25Z)
• MoEfication: Conditional Computation of Transformer Models for Efficient Inference [66.56994436947441]
  Transformer-based pre-trained language models can achieve superior performance on most NLP tasks due to large parameter capacity, but also lead to huge computation cost. We explore to accelerate large-model inference by conditional computation based on the sparse activation phenomenon. We propose to transform a large model into its mixture-of-experts (MoE) version with equal model size, namely MoEfication.
  arXiv  Detail & Related papers  (2021-10-05T02:14:38Z)
• Paired Examples as Indirect Supervision in Latent Decision Models [109.76417071249945]
  We introduce a way to leverage paired examples that provide stronger cues for learning latent decisions. We apply our method to improve compositional question answering using neural module networks on the DROP dataset.
  arXiv  Detail & Related papers  (2021-04-05T03:58:30Z)

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.