# CascadeDebate: Multi-Agent Deliberation for Cost-Aware LLM Cascades

arXiv: https://arxiv.org/abs/2604.12262 · HTML: https://mlsanity.com/paper/2604.12262/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 18 of its 26 references that are in the map.
- First posted on arXiv 14 Apr 2026.

## Placed in

- 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, 18 of 18)

- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams](https://mlsanity.com/paper/2009.13081/) (2020)
- [Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs](https://mlsanity.com/paper/2306.13063/) (2023)
- [FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance](https://mlsanity.com/paper/2305.05176/) (2023)
- [RouteLLM: Learning to Route LLMs with Preference Data](https://mlsanity.com/paper/2406.18665/) (2024)
- [Mixture-of-Agents Enhances Large Language Model Capabilities](https://mlsanity.com/paper/2406.04692/) (2024)
- [Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing](https://mlsanity.com/paper/2404.14618/) (2024)
- [Chain of Agents: Large Language Models Collaborating on Long-Context Tasks](https://mlsanity.com/paper/2406.02818/) (2024)
- [Large Language Model Cascades with Mixture of Thoughts Representations for Cost-efficient Reasoning](https://mlsanity.com/paper/2310.03094/) (2023)
- [A Unified Approach to Routing and Cascading for LLMs](https://mlsanity.com/paper/2410.10347/) (2024)
- [Multi-Agent Evolve: LLM Self-Improve through Co-evolution](https://mlsanity.com/paper/2510.23595/) (2025)
- [CortexDebate: Debating Sparsely and Equally for Multi-Agent Debate](https://mlsanity.com/paper/2507.03928/) (2025)
- [SATER: A Self-Aware and Token-Efficient Approach to Routing and Cascading](https://mlsanity.com/paper/2510.05164/) (2025)

## Built on by (most cited first, 3 of 3)

- [Engineering Reliable Coding Agents: Evaluating and Operating the System Around the Model](https://mlsanity.com/paper/2608.13867/) (2026)
- [KACE: Knowledge-Adaptive Context Engineering for Mathematical Reasoning](https://mlsanity.com/paper/2606.00532/) (2026)
- [Quantum Circuit Vision: Cost-Aware Evaluation of Visual AI Agents for Quantum Code Generation](https://mlsanity.com/paper/2607.10057/) (2026)

## Abstract (arXiv)

Cascaded LLM systems coordinate models of varying sizes with human experts to balance accuracy, cost, and abstention under uncertainty. However, single-model tiers at each stage often struggle with ambiguous queries, triggering premature escalations to costlier models or experts due to under-confidence and inefficient compute scaling. CascadeDebate addresses this gap by inserting multi-agent deliberation directly at each tier's escalation boundary. Confidence-based routers activate lightweight agent ensembles only for uncertain cases, enabling consensus-driven resolution of ambiguities internally without invoking higher-cost upgrades. Our unified architecture alternates single-model inference with selective multi-agent deliberation across model scales, culminating in human experts as the final fallback. This design scales test-time compute dynamically according to query difficulty. Across five benchmarks spanning science, medicine, and general knowledge, CascadeDebate outperforms strong single-model cascades and standalone multi-agent systems by up to 26.75 percent. An online threshold optimizer proves essential, boosting accuracy by 20.98 to 52.33 percent relative improvement over fixed policies and enabling elastic adaptation to real-world distributions.