Cover Image

Is Escalation Worth It? A Decision-Theoretic Characterization of LLM Cascades

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Bouchard, Dylan
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Uncertainty Quantification for Language Models: A Suite of Black-Box, White-Box, LLM Judge, and Ensemble Scorers
by: Bouchard, Dylan, et al.
Published: (2025)

Functional Entropy: Predicting Functional Correctness in LLM-Generated Code with Uncertainty Quantification
by: Bouchard, Dylan, et al.
Published: (2026)

Fine-Grained Uncertainty Quantification for Long-Form Language Model Outputs: A Comparative Study
by: Bouchard, Dylan, et al.
Published: (2026)

What is Your Data Worth to GPT? LLM-Scale Data Valuation with Influence Functions
by: Choe, Sang Keun, et al.
Published: (2024)

LangFair: A Python Package for Assessing Bias and Fairness in Large Language Model Use Cases
by: Bouchard, Dylan, et al.
Published: (2025)

UQLM: A Python Package for Uncertainty Quantification in Large Language Models
by: Bouchard, Dylan, et al.
Published: (2025)

Bring Your Own Prompts: Use-Case-Specific Bias and Fairness Evaluation for LLMs
by: Bouchard, Dylan
Published: (2024)

Efficient Contextual LLM Cascades through Budget-Constrained Policy Learning
by: Zhang, Xuechen, et al.
Published: (2024)

Turn Waste into Worth: Rectifying Top-$k$ Router of MoE
by: Zeng, Zhiyuan, et al.
Published: (2024)

Programming by Backprop: An Instruction is Worth 100 Examples When Finetuning LLMs
by: Cook, Jonathan, et al.
Published: (2025)

QUIET: A Multi-Blank Cascaded Story Cloze Benchmark for LLM Creative Generation Capability
by: Zou, Bo, et al.
Published: (2026)

Let Me Think! A Long Chain-of-Thought Can Be Worth Exponentially Many Short Ones
by: Mirtaheri, Parsa, et al.
Published: (2025)

$\textbf{Only-IF}$:Revealing the Decisive Effect of Instruction Diversity on Generalization
by: Zhang, Dylan, et al.
Published: (2024)

Evaluating LLM Understanding via Structured Tabular Decision Simulations
by: Li, Sichao, et al.
Published: (2025)

Tuning LLM Judge Design Decisions for 1/1000 of the Cost
by: Salinas, David, et al.
Published: (2025)

Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models
by: Wang, Boxin, et al.
Published: (2025)

From Words to Actions: Unveiling the Theoretical Underpinnings of LLM-Driven Autonomous Systems
by: He, Jianliang, et al.
Published: (2024)

Simple Yet Effective: An Information-Theoretic Approach to Multi-LLM Uncertainty Quantification
by: Kruse, Maya, et al.
Published: (2025)

Towards a Theoretical Understanding of Synthetic Data in LLM Post-Training: A Reverse-Bottleneck Perspective
by: Gan, Zeyu, et al.
Published: (2024)

The Reasoning Trap: An Information-Theoretic Bound on Closed-System Multi-Step LLM Reasoning
by: Shin, Kwan Soo
Published: (2026)

CORE: Measuring Multi-Agent LLM Interaction Quality under Game-Theoretic Pressures
by: Pandey, Punya Syon, et al.
Published: (2025)

Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation
by: Yang, Zhuolin, et al.
Published: (2026)

When LLM Judge Scores Look Good but Best-of-N Decisions Fail
by: Landesberg, Eddie
Published: (2026)

Beyond Behavioural Trade-Offs: Mechanistic Tracing of Pain-Pleasure Decisions in an LLM
by: Bianco, Francesca, et al.
Published: (2026)

Green Prompting: Characterizing Prompt-driven Energy Costs of LLM Inference
by: Adamska, Marta, et al.
Published: (2025)

Faster Cascades via Speculative Decoding
by: Narasimhan, Harikrishna, et al.
Published: (2024)

Why Reasoning Fails to Plan: A Planning-Centric Analysis of Long-Horizon Decision Making in LLM Agents
by: Wang, Zehong, et al.
Published: (2026)

Augmenting Legal Decision Support Systems with LLM-based NLI for Analyzing Social Media Evidence
by: Kadiyala, Ram Mohan Rao, et al.
Published: (2024)

ReflAct: World-Grounded Decision Making in LLM Agents via Goal-State Reflection
by: Kim, Jeonghye, et al.
Published: (2025)

"Oh LLM, I'm Asking Thee, Please Give Me a Decision Tree": Zero-Shot Decision Tree Induction and Embedding with Large Language Models
by: Knauer, Ricardo, et al.
Published: (2024)

Language Model Cascades: Token-level uncertainty and beyond
by: Gupta, Neha, et al.
Published: (2024)

A Theoretical Perspective for Speculative Decoding Algorithm
by: Yin, Ming, et al.
Published: (2024)

AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning
by: Xi, Zhiheng, et al.
Published: (2025)

Self-Improvement as Coherence Optimization: A Theoretical Account
by: Qiu, Tianyi, et al.
Published: (2026)

The Best Instruction-Tuning Data are Those That Fit
by: Zhang, Dylan, et al.
Published: (2025)

Wanting to be Understood
by: Fernando, Chrisantha, et al.
Published: (2025)

Instruction Diversity Drives Generalization To Unseen Tasks
by: Zhang, Dylan, et al.
Published: (2024)

A Communication-Theoretic Framework for LLM Agents: Cost-Aware Adaptive Reliability
by: Omidvar, Hamed, et al.
Published: (2026)

Training-Free Exponential Context Extension via Cascading KV Cache
by: Willette, Jeffrey, et al.
Published: (2024)

Translate Smart, not Hard: Cascaded Translation Systems with Quality-Aware Deferral
by: Farinhas, António, et al.
Published: (2025)