BEATS: Optimizing LLM Mathematical Capabilities with BackVerify and Adaptive Disambiguate based Efficient Tree Search

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sun, Linzhuang, Liang, Hao, Wei, Jingxuan, Yu, Bihui, He, Conghui, Zhou, Zenan, Zhang, Wentao
Format:	Preprint
Published:	2024
Subjects:	Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

MM-Verify: Enhancing Multimodal Reasoning with Chain-of-Thought Verification
by: Sun, Linzhuang, et al.
Published: (2025)

Synth-Empathy: Towards High-Quality Synthetic Empathy Data
by: Liang, Hao, et al.
Published: (2024)

Efficient-Empathy: Towards Efficient and Effective Selection of Empathy Data
by: Sun, Linzhuang, et al.
Published: (2024)

Rational Sensibility: LLM Enhanced Empathetic Response Generation Guided by Self-presentation Theory
by: Sun, Linzhuang, et al.
Published: (2023)

Geoint-R1: Formalizing Multimodal Geometric Reasoning with Dynamic Auxiliary Constructions
by: Wei, Jingxuan, et al.
Published: (2025)

Brain-inspired Computing Based on Deep Learning for Human-computer Interaction: A Review
by: Yu, Bihui, et al.
Published: (2023)

Rethinking Text-to-SQL: Dynamic Multi-turn SQL Interaction for Real-world Database Exploration
by: Sun, Linzhuang, et al.
Published: (2025)

Sentence-Level or Token-Level? A Comprehensive Study on Knowledge Distillation
by: Wei, Jingxuan, et al.
Published: (2024)

GGBench: A Geometric Generative Reasoning Benchmark for Unified Multimodal Models
by: Wei, Jingxuan, et al.
Published: (2025)

MathScape: Benchmarking Multimodal Large Language Models in Real-World Mathematical Contexts
by: Liang, Hao, et al.
Published: (2024)

LLaVA-NeuMT: Selective Layer-Neuron Modulation for Efficient Multilingual Multimodal Translation
by: Wei, Jingxuan, et al.
Published: (2025)

PAGER: Bridging the Semantic-Execution Gap in Point-Precise Geometric GUI Control
by: Wei, Jingxuan, et al.
Published: (2026)

Guided Verifier: Collaborative Multimodal Reasoning via Dynamic Process Supervision
by: Sun, Lingzhuang, et al.
Published: (2026)

KeyVideoLLM: Towards Large-scale Video Keyframe Selection
by: Liang, Hao, et al.
Published: (2024)

Boosting the Power of Small Multimodal Reasoning Models to Match Larger Models with Self-Consistency Training
by: Tan, Cheng, et al.
Published: (2023)

Retrieval Meets Reasoning: Even High-school Textbook Knowledge Benefits Multimodal Reasoning
by: Tan, Cheng, et al.
Published: (2024)

PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documents
by: Yu, Bihui, et al.
Published: (2026)

From Words to Structured Visuals: A Benchmark and Framework for Text-to-Diagram Generation and Editing
by: Wei, Jingxuan, et al.
Published: (2024)

TRACER: Verifiable Generative Provenance for Multimodal Tool-Using Agents
by: Yu, Bihui, et al.
Published: (2026)

How RL Unlocks the Aha Moment in Geometric Interleaved Reasoning
by: Zhang, Xiangxiang, et al.
Published: (2026)

A Survey on Image-text Multimodal Models
by: Guo, Ruifeng, et al.
Published: (2023)

Thinking with Drafting: Optical Decompression via Logical Reconstruction
by: Wei, Jingxuan, et al.
Published: (2026)

BEATS, DREAMS AND SHADOWS
by: Diego Juárez
Published: (2008)

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

Heterogeneous Adaptive Policy Optimization: Tailoring Optimization to Every Token's Nature
by: Liu, Zheng, et al.
Published: (2025)

ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning
by: Chen, Mingyang, et al.
Published: (2025)

SynthVLM: Towards High-Quality and Efficient Synthesis of Image-Caption Datasets for Vision-Language Models
by: Liu, Zheng, et al.
Published: (2024)

Data Proportion Detection for Optimized Data Management for Large Language Models
by: Liang, Hao, et al.
Published: (2024)

Gradual Learning: Optimizing Fine-Tuning with Partially Mastered Knowledge in Large Language Models
by: Li, Bozhou, et al.
Published: (2024)

N-BEATS-MOE: N-BEATS with a Mixture-of-Experts Layer for Heterogeneous Time Series Forecasting
by: Matos, Ricardo, et al.
Published: (2025)

Canvas-of-Thought: Grounding Reasoning via Mutable Structured States
by: Sun, Lingzhuang, et al.
Published: (2026)

Scholar Name Disambiguation with Search-enhanced LLM Across Language
by: Zhao, Renyu, et al.
Published: (2024)

HERMES: Towards Efficient and Verifiable Mathematical Reasoning in LLMs
by: Ospanov, Azim, et al.
Published: (2025)

K12-KGraph: A Curriculum-Aligned Knowledge Graph for Benchmarking and Training Educational LLMs
by: Liang, Hao, et al.
Published: (2026)

E2E: Efficient Filtered AKNN Search via Adaptive Termination
by: Xia, Wenxuan, et al.
Published: (2026)

Verifiable Model-Free Safety Filters via Reinforcement Learning
by: Yin, Bihui, et al.
Published: (2026)

Scaling Flaws of Verifier-Guided Search in Mathematical Reasoning
by: Yu, Fei, et al.
Published: (2025)

BRACE: A Benchmark for Robust Audio Caption Quality Evaluation
by: Guo, Tianyu, et al.
Published: (2025)

Pipeline for Verifying LLM-Generated Mathematical Solutions
by: Sazonova, Varvara, et al.
Published: (2026)

Dialogue Model Optimization via Agent Game and Adaptive Tree-based GRPO
by: Peng, Kun, et al.
Published: (2026)