ProgRouter: Online Progress-Guided Orchestration for Multi-Agent LLM Workflows under Quality-Cost Tradeoffs
cs.AI, cs.MA
Submitted: 2026-08-26
Updated: 2026-08-30
Comments: Accepted in Findings of the Association for Computational Linguistics: EMNLP 2026. Index Terms: Collaborative agentic workflows, LLM agent orchestration, Quality-cost trade-off, Task progress prediction, Online decision-making
License: http://creativecommons.org/licenses/by/4.0/
The gist: Multi-agent large language model (LLM) workflows have emerged as a powerful paradigm for solving complex, open-ended tasks through collaborative reasoning among specialized LLM agents, but they incur
Terminology
Abstract
Multi-agent large language model (LLM) workflows have emerged as a powerful paradigm for solving complex, open-ended tasks through collaborative reasoning among specialized LLM agents, but they incur substantial operating costs due to repeated LLM invocations and long-horizon context accumulation. Existing cascade routing methods make one-shot, query-level decisions and cannot adapt to the dynamic, state-dependent nature of multi-step workflows, in which the right LLM at each step depends on evolving task progress, remaining task difficulty, and cost-efficiency requirements. We present ProgRouter, an online progress-guided routing framework that adaptively selects LLM agents across workflow steps to preserve task-solving quality while adhering to time and cost budgets. ProgRouter introduces a multi-view task progress scorer that combines coarse workflow outcome regimes with fine-grained signals on subtask completion, progress trends, and workflow state quality. Then, a dual-path task progress predictor and an adaptive meta-gating mechanism estimate the progress gain for each candidate routed LLM. ProgRouter makes online step-wise routing decisions that balance progress gain, task time budgets, and long-term operating cost efficiency. Experiments on HumanEval Plus, MBPP, MATH-500, and ASQA, spanning agentic code generation, mathematical reasoning, and retrieval-augmented long-form question answering, demonstrate that ProgRouter reduces the operating cost relative to key baselines while maintaining strong task-solving performance.
Sources
- Program Synthesis with Large Language Models
- Qwen3-Coder-Next Technical Report
- Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks
- Qwen2.5-Coder Technical Report
- OpenAI GPT-5 System Card
- Stop Wasting Your Tokens: Towards Efficient Runtime Multi-Agent Systems
- DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models
- AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
- Reducing Cost of LLM Agents with Trajectory Reduction
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection