mlsanityData to 14 Oct 2026

Intelligence Under Time Constraints: Rethinking Test-Time Compute

arXiv 2609.14995 ↗First posted 14 Sep 2026cs.CLcited by 0

On the map: LLM reasoning → Test-time compute and efficient thinking

Abstract (arXiv)

Intelligence under time constraints requires deciding not only how much to compute, but when computation is worth starting. We study this problem in streaming interactions, where evidence arrives incrementally and may be revised. Early computation has more time to finish but rests on incomplete evidence; waiting improves information while shrinking computational slack. We call this the information-slack dilemma. We take the evidence-dependent computational job as the unit of analysis: when to start it, what supports its result, and when that result can be committed. Advance computation is valuable only insofar as its benefits survive the costs of verification, invalidation, and recovery. This applies to grounded incremental processing and reusable preparation as well as future-dependent speculation. We propose a research agenda on computation under evolving evidence, prioritizing selective recovery under controlled evidence revisions. Evaluation should separate earlier-execution effects, deployment value against a full-input alternative, and the added value of predictive policies, while accounting for shared-resource costs. The objective is not maximal advance computation, but more trustworthy, on-time responses within a declared resource envelope.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning. Builds on 5 of its 33 references that are in the map. First posted on arXiv 14 Sep 2026.

Builds on

5 of 33 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025Latency and Token-Aware Test-Time Compute11 Sep
  2. 2024Rational Metareasoning for Large Language Models7 Oct

Other references · 3

  1. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  2. 2024Large Language Monkeys: Scaling Inference Compute with Repeated Samplingcited by 991
  3. 2024LiveMind: Low-latency Large Language Models with Simultaneous Inferencecited by 10

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Interaction Scaling: Grounding the Third Axis of Test-Time Compute
  2. 2026Stop When Memory Suffices: Evidence-Conditioned Progressive Execution for LLM Agents
  3. 2026Free Energy Heuristics: Fast-And-Frugal Cognition as Active Inference Under Uncertain Precision
  4. 2026Rethinking Inference-Time Scaling in Local Computer-Use Agents: Failure Modes and Compute Tradeoffs
  5. 2026When More Thinking Hurts: Overthinking in LLM Test-Time Compute Scaling
  6. 2025Test-Time Scaling in Reasoning Models Is Not Effective for Knowledge-Intensive Tasks Yet
  7. 2026A Survey on Self-Improving Test-Time Intelligence: Feedback-Driven Adapting, Learning, and Scaling at Inference
  8. 2026What If We Allocate Test-Time Compute Adaptively?