Copertina

CircuitSeer: Mining High-Quality Data by Probing Mathematical Reasoning Circuits in LLMs

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wang, Shaobo, Miao, Yongliang, Liu, Yuancheng, Ma, Qianli, Liao, Ning, Zhang, Linfeng
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers
di: Liu, Jiacheng, et al.
Pubblicazione: (2025)

ImagebindDC: Compressing Multi-modal Data with Imagebind-based Condensation
di: Min, Yue, et al.
Pubblicazione: (2025)

AnomSeer: Reinforcing Multimodal LLMs to Reason for Time-Series Anomaly Detection
di: Zhang, Junru, et al.
Pubblicazione: (2026)

Decouple-Then-Merge: Finetune Diffusion Models as Multi-Task Learning
di: Ma, Qianli, et al.
Pubblicazione: (2024)

ReEfBench: Quantifying the Reasoning Efficiency of LLMs
di: Fu, Zhizhang, et al.
Pubblicazione: (2026)

SynCircuit: Automated Generation of New Synthetic RTL Circuits Can Enable Big Data in Circuits
di: Liu, Shang, et al.
Pubblicazione: (2025)

CircuitProbe: Predicting Reasoning Circuits in Transformers via Stability Zone Detection
di: Panuganti, Rajkiran
Pubblicazione: (2026)

SeerAttention-R: Sparse Attention Adaptation for Long Reasoning
di: Gao, Yizhao, et al.
Pubblicazione: (2025)

CIRCUIT: A Benchmark for Circuit Interpretation and Reasoning Capabilities of LLMs
di: Skelic, Lejla, et al.
Pubblicazione: (2025)

A Implies B: Circuit Analysis in LLMs for Propositional Logical Reasoning
di: Hong, Guan Zhe, et al.
Pubblicazione: (2024)

Socratic-Geo: Synthetic Data Generation and Geometric Reasoning via Multi-Agent Interaction
di: Jiao, Zhengbo, et al.
Pubblicazione: (2026)

Hierarchical Reasoning Models: Perspectives and Misconceptions
di: Ge, Renee, et al.
Pubblicazione: (2025)

LED-Merging: Mitigating Safety-Utility Conflicts in Model Merging with Location-Election-Disjoint
di: Ma, Qianli, et al.
Pubblicazione: (2025)

Credit Where It is Due: Cross-Modality Connectivity Drives Precise Reinforcement Learning for MLLM Reasoning
di: Jiao, Zhengbo, et al.
Pubblicazione: (2026)

Plan before Solving: Problem-Aware Strategy Routing for Mathematical Reasoning with LLMs
di: Qi, Shihao, et al.
Pubblicazione: (2025)

Do LLMs "Feel"? Emotion Circuits Discovery and Control
di: Wang, Chenxi, et al.
Pubblicazione: (2025)

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning
di: Zhang, Lin, et al.
Pubblicazione: (2025)

Hypothesis Testing the Circuit Hypothesis in LLMs
di: Shi, Claudia, et al.
Pubblicazione: (2024)

Spectral Probe-Circuits: A Three-Step Recipe for Identifying Attention-Head Circuits in Pretrained Transformers
di: Xu, Yongzhong
Pubblicazione: (2026)

MMCircuitEval: A Comprehensive Multimodal Circuit-Focused Benchmark for Evaluating LLMs
di: Zhao, Chenchen, et al.
Pubblicazione: (2025)

MathFimer: Enhancing Mathematical Reasoning by Expanding Reasoning Steps through Fill-in-the-Middle Task
di: Yan, Yuchen, et al.
Pubblicazione: (2025)

Revealing Algorithmic Deductive Circuits for Logical Reasoning
di: Nguyen, Phuong Minh, et al.
Pubblicazione: (2026)

ChipMind: Retrieval-Augmented Reasoning for Long-Context Circuit Design Specifications
di: Xing, Changwen, et al.
Pubblicazione: (2025)

Nuance Matters: Probing Epistemic Consistency in Causal Reasoning
di: Cui, Shaobo, et al.
Pubblicazione: (2024)

LLMs for Analog Circuit Design Continuum (ACDC)
di: Esfandiari, Yasaman, et al.
Pubblicazione: (2025)

Verifier-Backed Hard Problem Generation for Mathematical Reasoning
di: Lai, Yuhang, et al.
Pubblicazione: (2026)

Agentic Proposing: Enhancing Large Language Model Reasoning via Compositional Skill Synthesis
di: Jiao, Zhengbo, et al.
Pubblicazione: (2026)

Detecting Unfaithful Chain-of-Thought via Circuit-Guided Internal-External Discrepancy
di: Shen, Xu, et al.
Pubblicazione: (2026)

Circuit Diagram Retrieval Based on Hierarchical Circuit Graph Representation
di: Gao, Ming, et al.
Pubblicazione: (2025)

Enhancing Mathematical Reasoning in LLMs with Background Operators
di: Chen, Jiajun, et al.
Pubblicazione: (2024)

Restructuring Tractable Probabilistic Circuits
di: Zhang, Honghua, et al.
Pubblicazione: (2024)

Semantic Trajectory Data Mining with LLM-Informed POI Classification
di: Liu, Yifan, et al.
Pubblicazione: (2024)

Modeling Relational Logic Circuits for And-Inverter Graph Convolutional Network
di: Sun, Weihao, et al.
Pubblicazione: (2025)

DAG-Math: Graph-of-Thought Guided Mathematical Reasoning in LLMs
di: Zhang, Yuanhe, et al.
Pubblicazione: (2025)

AMSnet-q: Unsupervised Circuit Identification and Performance Labeling for AMS Circuits
di: Zhang, Ze, et al.
Pubblicazione: (2026)

Polynomial Semantics of Tractable Probabilistic Circuits
di: Broadrick, Oliver, et al.
Pubblicazione: (2024)

What to Ask Next? Probing the Imaginative Reasoning of LLMs with TurtleSoup Puzzles
di: Zhou, Mengtao, et al.
Pubblicazione: (2025)

Reasoning Like an Economist: Post-Training on Economic Problems Induces Strategic Generalization in LLMs
di: Zhou, Yufa, et al.
Pubblicazione: (2025)

Inverse Design in Distributed Circuits Using Single-Step Reinforcement Learning
di: Li, Jiayu, et al.
Pubblicazione: (2025)

From Implicit to Explicit: Token-Efficient Logical Supervision for Mathematical Reasoning in LLMs
di: Wang, Shaojie, et al.
Pubblicazione: (2026)