CIFLEX: Contextual Instruction Flow for Sub-task Execution in Multi-Turn Interactions with a Single On-Device LLM

• URL: http://arxiv.org/abs/2510.01239v1
• Date: Wed, 24 Sep 2025 01:20:47 GMT
• Title: CIFLEX: Contextual Instruction Flow for Sub-task Execution in Multi-Turn Interactions with a Single On-Device LLM
• Abstract summary: We present a novel execution system for efficient sub-task handling in multi-turn interactions with a single on-device large language model (LLM)<n>We develop a hierarchical classification strategy tailored for small-scale models, decomposing multi-choice decisions into binary ones.<n>Experiments show that CIFLEX significantly reduces computational costs without degrading task performance, enabling scalable and efficient multi-task dialogue on-device.
• Score: 25.486389526043727
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present CIFLEX (Contextual Instruction Flow for Sub-task Execution), which is a novel execution system for efficient sub-task handling in multi-turn interactions with a single on-device large language model (LLM). As LLMs become increasingly capable, a single model is expected to handle diverse sub-tasks that more effectively and comprehensively support answering user requests. Naive approach reprocesses the entire conversation context when switching between main and sub-tasks (e.g., query rewriting, summarization), incurring significant computational overhead. CIFLEX mitigates this overhead by reusing the key-value (KV) cache from the main task and injecting only task-specific instructions into isolated side paths. After sub-task execution, the model rolls back to the main path via cached context, thereby avoiding redundant prefill computation. To support sub-task selection, we also develop a hierarchical classification strategy tailored for small-scale models, decomposing multi-choice decisions into binary ones. Experiments show that CIFLEX significantly reduces computational costs without degrading task performance, enabling scalable and efficient multi-task dialogue on-device.

Related papers

• Learning to Share: Selective Memory for Efficient Parallel Agentic Systems [49.78267008828593]
  Agentic systems solve complex tasks by coordinating multiple agents that iteratively reason, invoke tools, and exchange intermediate results.<n>Recent approaches deploy multiple agent teams running in parallel to explore diverse reasoning trajectories.<n>We propose Learning to Share (LTS), a learned shared-memory mechanism for parallel agentic frameworks.
  arXiv  Detail & Related papers  (2026-02-05T18:20:21Z)
• Stay Unique, Stay Efficient: Preserving Model Personality in Multi-Task Merging [62.61159948488935]
  Decomposition, Thresholding, and Scaling (DTS) is an approximation-based personalized merging framework.<n>DTS preserves task-specific information with minimal storage overhead.<n>We extend DTS with a variant that fuses task-specific information in a data-free manner based on the semantic similarity of task characteristics.
  arXiv  Detail & Related papers  (2025-12-01T09:47:17Z)
• On-device System of Compositional Multi-tasking in Large Language Models [29.561801948704822]
  We propose a novel approach tailored specifically for compositional multi-tasking scenarios involving summarization and translation.<n>Our technique involves adding a learnable projection layer on top of the combined summarization and translation adapters.<n>We demonstrate the practical viability of our method within an on-device environment by developing an Android app capable of executing compositional tasks seamlessly.
  arXiv  Detail & Related papers  (2025-10-11T19:49:22Z)
• Efficient Compositional Multi-tasking for On-device Large Language Models [19.179619181605556]
  We study the problem of text-based compositional multi-tasking, where each test example involves the simultaneous execution of multiple tasks.<n>Our contributions lay the groundwork for advancing the capabilities of large language models in real-world multi-tasking scenarios, expanding their applicability to complex, resource-constrained use cases.
  arXiv  Detail & Related papers  (2025-07-21T21:39:23Z)
• Route-and-Reason: Scaling Large Language Model Reasoning with Reinforced Model Router [9.580226379350737]
  Multi-step reasoning has proven essential for enhancing the problem-solving capabilities of Large Language Models.<n>Yet, many reasoning steps are relatively simple and can be handled by more efficient smaller-scale language models.<n>We propose R2-Reasoner, a novel framework that enables collaborative reasoning across heterogeneous LLMs.
  arXiv  Detail & Related papers  (2025-06-06T09:18:56Z)
• Division-of-Thoughts: Harnessing Hybrid Language Model Synergy for Efficient On-Device Agents [5.566936703366701]
  Division-of-Thoughts (DoT) is a collaborative reasoning framework leveraging the synergy between local and cloud-based language models.<n>DoT reduces the average reasoning time and API costs by 66.12% and 83.57%, while achieving comparable reasoning accuracy with the best baseline methods.
  arXiv  Detail & Related papers  (2025-02-06T02:40:25Z)
• QPO: Query-dependent Prompt Optimization via Multi-Loop Offline Reinforcement Learning [58.767866109043055]
  We introduce Query-dependent Prompt Optimization (QPO), which iteratively fine-tune a small pretrained language model to generate optimal prompts tailored to the input queries.<n>We derive insights from offline prompting demonstration data, which already exists in large quantities as a by-product of benchmarking diverse prompts on open-sourced tasks.<n> Experiments on various LLM scales and diverse NLP and math tasks demonstrate the efficacy and cost-efficiency of our method in both zero-shot and few-shot scenarios.
  arXiv  Detail & Related papers  (2024-08-20T03:06:48Z)
• Sweeping Heterogeneity with Smart MoPs: Mixture of Prompts for LLM Task Adaptation [43.32632163091792]
  Large Language Models (LLMs) have the ability to solve a variety of tasks, such as text summarization and mathematical questions.<n>Due to high computational costs, the current trend is to use prompt instruction tuning to better adjust monolithic, pretrained LLMs for new -- but often individual -- downstream tasks.<n>MoPs can simultaneously mitigate prompt training "interference" in multi-task, multi-source scenarios.
  arXiv  Detail & Related papers  (2023-10-04T14:11:12Z)
• Decomposed Prompting: A Modular Approach for Solving Complex Tasks [55.42850359286304]
  We propose Decomposed Prompting to solve complex tasks by decomposing them (via prompting) into simpler sub-tasks. This modular structure allows each prompt to be optimized for its specific sub-task. We show that the flexibility and modularity of Decomposed Prompting allows it to outperform prior work on few-shot prompting.
  arXiv  Detail & Related papers  (2022-10-05T17:28:20Z)
• Task Adaptive Parameter Sharing for Multi-Task Learning [114.80350786535952]
  Adaptive Task Adapting Sharing (TAPS) is a method for tuning a base model to a new task by adaptively modifying a small, task-specific subset of layers. Compared to other methods, TAPS retains high accuracy on downstream tasks while introducing few task-specific parameters. We evaluate our method on a suite of fine-tuning tasks and architectures (ResNet, DenseNet, ViT) and show that it achieves state-of-the-art performance while being simple to implement.
  arXiv  Detail & Related papers  (2022-03-30T23:16:07Z)
• Exploring Relational Context for Multi-Task Dense Prediction [76.86090370115]
  We consider a multi-task environment for dense prediction tasks, represented by a common backbone and independent task-specific heads. We explore various attention-based contexts, such as global and local, in the multi-task setting. We propose an Adaptive Task-Relational Context module, which samples the pool of all available contexts for each task pair.
  arXiv  Detail & Related papers  (2021-04-28T16:45:56Z)

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.