Budget-Aware LLM Discovery via Cost-Calibrated Frontier Utility

arXiv:2607.26828 · cs.LG, cs.AI · Submitted 2026-07-29 · Read on arXiv

cs.LG, cs.AI

Submitted: 2026-07-29

Updated: 2026-09-26

Code: https://github.com/Forrest-Stone/CostAda

Project page: https://erich-friedman.github.io/packing

Terminology

• Benchmark — 105× in this paper · explained in 2 episodes
• AUC — 12× in this paper · explained in 2 episodes
• Calibration — 12× in this paper · explained in 7 episodes
• Trace — 7× in this paper · explained in 2 episodes
• Ablation — 5× in this paper · explained in 1 episode
• Core — 3× in this paper · explained in 2 episodes
• Agentic System — 2× in this paper · explained in 2 episodes
• International Digital Economy Academy — 2× in this paper
• Adam — 1× in this paper · explained in 2 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Multi-Agent System — 1× in this paper · explained in 6 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Test-time Scaling — 1× in this paper · explained in 2 episodes

Sources

• The Art of Scaling Test-Time Compute for Large Language Models
• GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
• Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMs
• CodeEvolve: an open source evolutionary coding agent for algorithmic discovery and optimization
• AdaEvolve: Adaptive LLM Driven Zeroth-Order Optimization
• Inference-Time Budget Control for LLM Search Agents
• DeltaEvolve: Accelerating Scientific Discovery through Momentum-Driven Evolution
• ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution
• SelfBudgeter: Adaptive Token Allocation for Efficient LLM Reasoning
• EvoX: Meta-Evolution for Automated Discovery
• Budget-Aware Tool-Use Enables Effective Agent Scaling
• Aligning Tree-Search Policies with Fixed Token Budgets in Test-Time Scaling of LLMs
• AlphaEvolve: A coding agent for scientific and algorithmic discovery
• CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery
• BudgetThinker: Empowering Budget-aware LLM Reasoning with Control Tokens
• Compute Allocation for Self-Evolving LLMs: From Depth-Breadth to Multi-Armed Bandits
• TurboEvolve: Towards Fast and Robust LLM-Driven Program Evolution
• Structured Scaling of AI Discovery Across Diverse Scientific Domains

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks