# Arbor: A Framework for Reliable Navigation of Critical Conversation Flows

arXiv: https://arxiv.org/abs/2602.14643 · HTML: https://mlsanity.com/paper/2602.14643/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 25 references that are in the map.
- First posted on arXiv 16 Feb 2026.

## Builds on (most cited first, 12 of 12)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Graph of Thoughts: Solving Elaborate Problems with Large Language Models](https://mlsanity.com/paper/2308.09687/) (2023)
- [Compressing Context to Enhance Inference Efficiency of Large Language Models](https://mlsanity.com/paper/2310.06201/) (2023)
- [CoD, Towards an Interpretable Medical Agent using Chain of Diagnosis](https://mlsanity.com/paper/2407.13301/) (2024)
- [LIFBench: Evaluating the Instruction Following Performance and Stability of Large Language Models in Long-Context Scenarios](https://mlsanity.com/paper/2411.07037/) (2024)
- [Frontier LLMs Still Struggle with Simple Reasoning Tasks](https://mlsanity.com/paper/2507.07313/) (2025)
- [Enhancing Large Language Models for Clinical Decision Support by Incorporating Clinical Practice Guidelines](https://mlsanity.com/paper/2401.11120/) (2024)
- [Decoupling Task-Solving and Output Formatting in LLM Generation](https://mlsanity.com/paper/2510.03595/) (2025)
- [A Novel Architecture for Symbolic Reasoning with Decision Trees and LLM Agents](https://mlsanity.com/paper/2508.05311/) (2025)
- [Alquist 5.0: Dialogue Trees Meet Generative Models. A Novel Approach for Enhancing SocialBot Conversations](https://mlsanity.com/paper/2310.16119/) (2023)

## Abstract (arXiv)

Large language models struggle to maintain strict adherence to structured workflows in high-stakes domains such as healthcare triage. Monolithic approaches that encode entire decision structures within a single prompt are prone to instruction-following degradation as prompt length increases, including lost-in-the-middle effects and context window overflow. To address this gap, we present Arbor, a framework that decomposes decision tree navigation into specialized, node-level tasks. Decision trees are standardized into an edge-list representation and stored for dynamic retrieval. At runtime, a directed acyclic graph (DAG)-based orchestration mechanism iteratively retrieves only the outgoing edges of the current node, evaluates valid transitions via a dedicated LLM call, and delegates response generation to a separate inference step. The framework is agnostic to the underlying decision logic and model provider. Evaluated against single-prompt baselines across 10 foundation models using annotated turns from real clinical triage conversations. Arbor improves mean turn accuracy by 29.4 percentage points, reduces per-turn latency by 57.1%, and achieves an average 13.8x reduction in per-turn cost. These results indicate that architectural decomposition reduces dependence on intrinsic model capability, enabling smaller models to match or exceed larger models operating under single-prompt baselines.