Preregistered placebo-controlled decomposition shows external executable counterexamples drive self-repair gains in small code models more than re-exposure or self-critique.
Learning how hard to think: Input-adaptive allocation of lm computation.arXiv preprint arXiv:2410.04707
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
verdicts
UNVERDICTED 8roles
method 1polarities
use method 1representative citing papers
ATLAS introduces an LLM-orchestrated agentic framework for dynamic test-time scaling via extensible 'explore' actions, achieving higher accuracy with fewer API calls than fixed-workflow baselines on four benchmarks.
GPS trains a small model on optimization history to predict prompt difficulty and select intermediate-difficulty diverse batches, yielding better training efficiency, final performance, and test-time allocation than baselines on reasoning benchmarks.
o1-like models overthink easy tasks; self-training reduces compute use without accuracy loss on GSM8K, MATH500, GPQA, and AIME.
SSOPD converts intra-group correct-wrong contrast into process supervision by distilling a teacher distribution from the shortest correct completion into prefixes of the longest wrong completion, improving GRPO on AIME and HMMT benchmarks.
DMoA is a differentiable multi-agent framework for LLMs that uses recurrent context-aware routing and predictive entropy for test-time adaptation, claiming SOTA results on 9 benchmarks with efficiency and robustness.
GlimpRouter uses the entropy of the first token in each reasoning step to decide whether to invoke a large model, yielding 10.7% higher accuracy and 25.9% lower latency than a standalone large model on AIME25.
Calibrate-Then-Act supplies LLM agents with priors on latent environment states to enable explicit cost-uncertainty reasoning, producing more optimal strategies than standard approaches in retrieval QA and file-reading coding tasks.
citing papers explorer
-
Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs
o1-like models overthink easy tasks; self-training reduces compute use without accuracy loss on GSM8K, MATH500, GPQA, and AIME.