Cover Image

Predicting LLM Reasoning Performance with Small Proxy Model

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Koh, Woosung, Suk, Juyoung, Han, Sungjun, Yun, Se-Young, Shin, Jamin
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Generative Visual Code Mobile World Models
by: Koh, Woosung, et al.
Published: (2026)

Trillion 7B Technical Report
by: Han, Sungjun, et al.
Published: (2025)

mSFT: Addressing Dataset Mixtures Overfitting Heterogeneously in Multi-task SFT
by: Koh, Woosung, et al.
Published: (2026)

Extreme Solar Flare Prediction Using Residual Networks with HMI Magnetograms and Intensitygrams
by: Yun, Juyoung, et al.
Published: (2024)

FlickerFusion: Intra-trajectory Domain Generalizing Multi-Agent RL
by: Koh, Woosung, et al.
Published: (2024)

Analysis and Predictive Modeling of Solar Coronal Holes Using Computer Vision and ARIMA-LSTM Networks
by: Yun, Juyoung, et al.
Published: (2024)

$C^2$: Scalable Auto-Feedback for LLM-based Chart Generation
by: Koh, Woosung, et al.
Published: (2024)

Mitigating Gradient Overlap in Deep Residual Networks with Gradient Normalization for Improved Non-Convex Optimization
by: Yun, Juyoung
Published: (2024)

AdaSTaR: Adaptive Data Sampling for Training Self-Taught Reasoners
by: Koh, Woosung, et al.
Published: (2025)

What is the Alignment Objective of GRPO?
by: Vojnovic, Milan, et al.
Published: (2025)

DistiLLM: Towards Streamlined Distillation for Large Language Models
by: Ko, Jongwoo, et al.
Published: (2024)

Temporal Alignment Guidance: On-Manifold Sampling in Diffusion Models
by: Park, Youngrok, et al.
Published: (2025)

ProxyKV: Cross-Model Proxy Pruning for Efficient Long-Context LLM Inference
by: Li, Junjie, et al.
Published: (2026)

Encoding Temporal Statistical-space Priors via Augmented Representation
by: Choi, Insu, et al.
Published: (2024)

Curriculum Learning and Imitation Learning for Model-free Control on Financial Time-series
by: Koh, Woosung, et al.
Published: (2023)

Self-Refinement of Language Models from External Proxy Metrics Feedback
by: Ramji, Keshav, et al.
Published: (2024)

Self-Training Elicits Concise Reasoning in Large Language Models
by: Munkhbat, Tergel, et al.
Published: (2025)

The Hidden Power of Pure 16-bit Floating-Point Neural Networks
by: Yun, Juyoung, et al.
Published: (2023)

Stochastic Gradient Sampling for Enhancing Neural Networks Training
by: Yun, Juyoung
Published: (2023)

RetroReasoner: A Reasoning LLM for Strategic Retrosynthesis Prediction
by: Ko, Hanbum, et al.
Published: (2026)

Contextual Linear Bandits under Noisy Features: Towards Bayesian Oracles
by: Kim, Jung-hun, et al.
Published: (2017)

Small Generalizable Prompt Predictive Models Can Steer Efficient RL Post-Training of Large Reasoning Models
by: Qu, Yun, et al.
Published: (2026)

Can Small Training Runs Reliably Guide Data Curation? Rethinking Proxy-Model Practice
by: Wang, Jiachen T., et al.
Published: (2025)

Conditional Synthesis of 3D Molecules with Time Correction Sampler
by: Jung, Hojung, et al.
Published: (2024)

A Hierarchical Language Model with Predictable Scaling Laws and Provable Benefits of Reasoning
by: Gaitonde, Jason, et al.
Published: (2026)

DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs
by: Ko, Jongwoo, et al.
Published: (2025)

The Reasoning Trap: An Information-Theoretic Bound on Closed-System Multi-Step LLM Reasoning
by: Shin, Kwan Soo
Published: (2026)

Dynamics-Predictive Sampling for Active RL Finetuning of Large Reasoning Models
by: Mao, Yixiu, et al.
Published: (2026)

Automated Filtering of Human Feedback Data for Aligning Text-to-Image Diffusion Models
by: Yang, Yongjin, et al.
Published: (2024)

Disentangled Sparse Representations for Concept-Separated Diffusion Unlearning
by: Kim, Hyeonjin, et al.
Published: (2026)

Revisiting Multi-Agent Debate as Test-Time Scaling: A Systematic Study of Conditional Effectiveness
by: Yang, Yongjin, et al.
Published: (2025)

Automated Skill Discovery for Language Agents through Exploration and Iterative Feedback
by: Yang, Yongjin, et al.
Published: (2025)

Towards Mitigating Excessive Forgetting in LLM Unlearning via Entanglement-Guidance with Proxy Constraint
by: Liu, Zhihao, et al.
Published: (2025)

Can Prompt Difficulty be Online Predicted for Accelerating RL Finetuning of Reasoning Models?
by: Qu, Yun, et al.
Published: (2025)

Enhancing Reasoning Capabilities of Small Language Models with Blueprints and Prompt Template Search
by: Han, Dongge, et al.
Published: (2025)

Proxy-RLHF: Decoupling Generation and Alignment in Large Language Model with Proxy
by: Zhu, Yu, et al.
Published: (2024)

FairDICE: Fairness-Driven Offline Multi-Objective Reinforcement Learning
by: Kim, Woosung, et al.
Published: (2025)

RAST: Reasoning Activation in LLMs via Small-model Transfer
by: Ouyang, Siru, et al.
Published: (2025)

Lightweight Dataset Pruning without Full Training via Example Difficulty and Prediction Uncertainty
by: Cho, Yeseul, et al.
Published: (2025)

CaliciBoost: Performance-Driven Evaluation of Molecular Representations for Caco-2 Permeability Prediction
by: Van Le, Huong, et al.
Published: (2025)