AIarXiv
Heuristic editor, no API keyVerdict: NotableFrom Pareto to Preference: Personalized Test-Time Scaling via Amortized Agentic Policy Discovery
Test-time scaling (TTS) improves the reasoning capabilities of large language models by allocating additional inference computation.
Caveats
- Preprint; not yet peer reviewed.
VerdictWorth a reader's time today.
Abstract
Test-time scaling (TTS) improves the reasoning capabilities of large language models by allocating additional inference computation. Existing approaches to improving TTS efficiency largely optimize accuracy against one resource dimension at a time, advancing either the accuracy--cost or accuracy--latency Pareto frontier. Yet user requirements are multidimensional: users may specify accuracy, latency, and inference-cost requirements jointly, and different requirements can favor different controllers. We formulate Personalized Test-Time Scaling as discovering executable controllers that maximize the joint satisfaction rate of user-specific requirements. To reduce the overhead of repeated policy discovery for new user profiles, we propose PersonTTS, an amortized agentic policy-discovery framework that reuses prior search experience through requirement-matched controller initialization and source-distilled procedural guidance, while retaining target-profile evaluation for every candidate. Experiments on AIME and HMMT show that PersonTTS substantially outperforms strong TTS baselines in joint requirement satisfaction on unseen user profiles and held-out problems. Under the same candidate-evaluation budget, cross-user experience reuse further improves policy quality while substantially reducing discovery-agent time and cost.
The editor's rubric
| Dimension | Level | Weight | What that level means |
|---|---|---|---|
| Leverage | ███░░ 3 | 24% | A method or resource many groups across the field will adopt within a year. |
| Magnitude | ███░░ 3 | 18% | Large gain: roughly 2x, or a clear new state of the art on a hard, unsaturated problem. |
| Evidence | ███░░ 3 | 14% | Solid: multiple benchmarks or cohorts, ablations, fair baselines, released code or data. |
| Novelty | ███░░ 3 | 16% | A genuinely new approach to an open problem. |
| Trajectory | ███░░ 3 | 18% | A clear path to scale. |
| Stakes | ██░░░ 2 | 10% | Benefits a professional community (practitioners, clinicians, engineers). |
Editor’s rationale
Heuristic triage from title and abstract text only, not a reading of the paper. Cues found: method (we propose); gains (outperforms); novelty (discovery); verification (held-out test); scale (scalable, efficient); stakes (general AI).
How the score was computed
- Merit
- 5.8 / 10
- Adjusted merit
- 4.8 / 10
- Attention
- 43%
- Freshness
- 27%
- Citations0 (reference 15, via semantic-scholar, Oct 10, 2026, 13:49 UTC)
- Influential citations0 (reference 3, via semantic-scholar, Oct 10, 2026, 13:49 UTC)
- Hugging Face upvotes16 (reference 25, via hf-daily, Oct 10, 2026, 13:49 UTC)
- GitHub stars2 (reference 250, via hf-daily, Oct 10, 2026, 13:49 UTC)