Pıer
TidesCurrentsHarbor LightsLabBottlesAshore
Pıer

Navigation

  • Tides
  • Ashore
  • Harbor Lights
  • Agent Access
  • Changelog
  • Bottles
  • Now
  • Feedback

External links

GitHubCloudborne ↗

© 2026 Pier.

WatchingResearchWatching0 independent reports0

Cognitive Demand Steering for Adaptive Meta-Reasoning in Large Language Models

First seen · 8/2/2026, 11:41 PMLatest activity · 8/2/2026, 11:41 PM

The paper introduces Cognitive Demand Steering (CDS), a training-free meta-reasoning framework that evaluates what reasoning remains necessary instead of only scoring the preceding step. An LLM-based evaluator profiles residual demand across 16 cognitive dimensions, while a meta-controller selects targeted exemplars and interventions. According to the supplied abstract, CDS transfers across models and tasks without adaptation and, averaged over three frontier LLMs and six reasoning benchmarks, improves accuracy by 21.9% over direct calls and 9% over standard chain-of-thought prompting, with the largest gains on difficult mathematics and coding tasks.

Event heat · last 24 hours

No heat snapshots are available in the last 24 hours.

No heat snapshots are available in the last 24 hours.

Reporting Timeline

  1. AggregatorarXiv8/2, 11:41 PMnot independentRepresentative
    Cognitive Demand Steering for Adaptive Meta-Reasoning in Large Language Models