← All concepts

test-time scaling

When a model faces a hard problem, you can spend extra computation after the first answer, generating many candidates and picking the best, or refining previous attempts step by step. That extra inference-time compute is test-time scaling. It lets models improve without retraining, but the compute must be spent wisely.

Across these studies, the common lesson is that naively generating more samples saturates. Gains come instead from increasing diversity, filtering low-confidence tokens, switching models when progress stalls, using external checks, and treating submission failures as separate from correct candidates. Other work makes scaling practical by certifying sample budgets, compressing memory, or composing optimization strategies adaptively. Together they shift toward smarter, budget-aware allocation of inference compute.

Papers
117
Released code
7
First seen
Aug 2026
Latest
Nov 2026

116 papers in the last two months, against 1 in the two before.

Start here

Three papers to read first, in the order they came out
  1. 1Giving harder inputs more attempts helps little on hard LLM workloads

    Giving harder inputs more repeated attempts by an LLM pays off only when the budget is large relative to difficulty; otherwise the optimal allocation is inverted-U.

    Nov 2026
  2. 2AI agents can score higher by keeping luckier simulated outcomes

    Branch-and-commit only improves performance when candidate returns vary, and most gain is from selecting among random outcomes rather than better actions.

    Nov 2026
  3. 3Multi-agent LLMs fail to outperform single-agent sampling when compute is matched

    Multi-agent language models do not improve accuracy over single-agent systems when compute budgets are matched.

    Nov 2026

Who is working on it

Carnegie Mellon University 5Stanford University 5Amazon 4National University of Singapore 4Tsinghua University 4Apple 3

The papers

Most central to this idea first, not most recent.

Concepts are extracted from each paper and reused across the corpus, so this page grows on its own as the desk reads.