AI ethics evidence index Search
Source-linked daily record
Evidence record 17917 · automatically gathered

CoBa: Cost-Effective Test-Time Scaling via Compute-Balanced Routing

Test-time scaling is often implemented by spending more compute along one axis: sampling more solutions, extending a chain of thought, or applying a stronger evaluator. Under a fixed inference budget, these choices compete. This paper formulates test-time reasoning as a compute-allocation problem in which a system must decide whether the next unit of compute should be spent on generation, verification, or stopping. We introduce CoBa, a compute-balanced routing policy that first obtains a small s

Record details

Published: 7 August 2026
Source: arXiv cs.AI
Category: Research
Topics: Regulation
Retrieved: 10 August 2026

source-onlyevidence status

These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.

Same publisher byline

TEPA: Revoking Stale Memories for Conflict-Robust Language Agents

arXiv cs.AI · 7 August 2026

Shared topic: Regulation

Taxonomy-Driven Analysis of Open-Source AI Risk Mitigation Tools

arXiv · 7 August 2026

Shared topic: Regulation

From Forensics to Ecosystems: Rethinking Watermarks for Generative AI Oversight

arXiv · 7 August 2026

Shared topic: Regulation

Aftab: A Comprehensive Benchmark of CNN Encoders and Advanced Value Functions in Parallelized Q-Networks

arXiv cs.AI · 7 August 2026

Shared topic: Regulation

Ego-OSCAR: Egocentric Open source Stereo CAptuRe System

HuggingFace Daily Papers · 7 August 2026

Shared topic: Regulation

Reading Copom's Tone: A Weighted LLM Framework for Hawkish-Dovish Sentiment, Forward Guidance, and Uncertainty

arXiv cs.AI · 7 August 2026

How to cite this record

ethics.ai (7 August 2026), “CoBa: Cost-Effective Test-Time Scaling via Compute-Balanced Routing,” evidence record 17917, https://ethics.ai/record/17917 (originally published by arXiv cs.AI).

JSON

Use and limitations

This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.