Imagen de Portada

Beyond Token-Level Policy Gradients for Complex Reasoning with Large Language Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Xu, Mufan, Chen, Kehai, Bai, Xuefeng, Niu, Zhengyu, Yang, Muyun, Zhao, Tiejun, Zhang, Min
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

LLM-based Discriminative Reasoning for Knowledge Graph Question Answering
por: Xu, Mufan, et al.
Publicado: (2024)

Thinking in Character: Advancing Role-Playing Agents with Role-Aware Reasoning
por: Tang, Yihong, et al.
Publicado: (2025)

Large Language Models for Classical Chinese Poetry Translation: Benchmarking, Evaluating, and Improving
por: Chen, Andong, et al.
Publicado: (2024)

DUAL-REFLECT: Enhancing Large Language Models for Reflective Translation through Dual Learning Feedback Mechanisms
por: Chen, Andong, et al.
Publicado: (2024)

Memory-augmented Query Reconstruction for LLM-based Knowledge Graph Reasoning
por: Xu, Mufan, et al.
Publicado: (2025)

User-Aware Active Knowledge Acquisition for Emotional Support Dialogue
por: Xu, Mufan, et al.
Publicado: (2026)

A Survey on Human Preference Learning for Large Language Models
por: Jiang, Ruili, et al.
Publicado: (2024)

LLM-based Translation Inference with Iterative Bilingual Understanding
por: Chen, Andong, et al.
Publicado: (2024)

Make Imagination Clearer! Stable Diffusion-based Visual Imagination for Multimodal Machine Translation
por: Chen, Andong, et al.
Publicado: (2024)

Evaluating o1-Like LLMs: Unlocking Reasoning for Translation through Comprehensive Analysis
por: Chen, Andong, et al.
Publicado: (2025)

Instruction Anchor: Dissecting the Mechanistic Dynamics of Modality Arbitration
por: Zhang, Yu, et al.
Publicado: (2026)

Agentic Tool Use in Large Language Models
por: Hu, Jinchao, et al.
Publicado: (2026)

Benchmarking and Improving Large Vision-Language Models for Fundamental Visual Graph Understanding and Reasoning
por: Zhu, Yingjie, et al.
Publicado: (2024)

Exploring the Translation Mechanism of Large Language Models
por: Zhang, Hongbin, et al.
Publicado: (2025)

Paying More Attention to Source Context: Mitigating Unfaithful Translations from Large Language Model
por: Zhang, Hongbin, et al.
Publicado: (2024)

LinguaLIFT: An Effective Two-stage Instruction Tuning Framework for Low-Resource Language Reasoning
por: Zhang, Hongbin, et al.
Publicado: (2024)

Generator-Assistant Stepwise Rollback Framework for Large Language Model Agent
por: Li, Xingzuo, et al.
Publicado: (2025)

Look Before You Leap: Enhancing Attention and Vigilance Regarding Harmful Content with GuidelineLLM
por: Zhang, Shaoqing, et al.
Publicado: (2024)

The Rise of Darkness: Safety-Utility Trade-Offs in Role-Playing Dialogue Agents
por: Tang, Yihong, et al.
Publicado: (2025)

TF-Attack: Transferable and Fast Adversarial Attacks on Large Language Models
por: Li, Zelin, et al.
Publicado: (2024)

The Power of Personality: A Human Simulation Perspective to Investigate Large Language Model Agents
por: Duan, Yifan, et al.
Publicado: (2025)

Efficient Safety Alignment of Large Language Models via Preference Re-ranking and Representation-based Reward Modeling
por: Deng, Qiyuan, et al.
Publicado: (2025)

Evaluating and Steering Modality Preferences in Multimodal Large Language Model
por: Zhang, Yu, et al.
Publicado: (2025)

Beyond the Vision Encoder: Identifying and Mitigating Spatial Bias in Large Vision-Language Models
por: Zhu, Yingjie, et al.
Publicado: (2025)

Toward Robust LLM-Based Judges: Taxonomic Bias Evaluation and Debiasing Optimization
por: Zhou, Hongli, et al.
Publicado: (2026)

Evaluating and Improving Cultural Awareness of Reward Models for LLM Alignment
por: Zhang, Hongbin, et al.
Publicado: (2025)

From Perception to Reasoning: Deep Thinking Empowers Multimodal Large Language Models
por: Zhu, Wenxin, et al.
Publicado: (2025)

Beyond Unimodal Shortcuts: MLLMs as Cross-Modal Reasoners for Grounded Named Entity Recognition
por: Ma, Jinlong, et al.
Publicado: (2026)

Lost in Benchmarks? Rethinking Large Language Model Benchmarking with Item Response Theory
por: Zhou, Hongli, et al.
Publicado: (2025)

XIFBench: Evaluating Large Language Models on Multilingual Instruction Following
por: Li, Zhenyu, et al.
Publicado: (2025)

Self-Evaluation of Large Language Model based on Glass-box Features
por: Huang, Hui, et al.
Publicado: (2024)

HITSZ's End-To-End Speech Translation Systems Combining Sequence-to-Sequence Auto Speech Recognition Model and Indic Large Language Model for IWSLT 2025 in Indic Track
por: Wei, Xuchen, et al.
Publicado: (2025)

Mitigating the Bias of Large Language Model Evaluation
por: Zhou, Hongli, et al.
Publicado: (2024)

Through the Lens of Character: Resolving Modality-Role Interference in Multimodal Role-Playing Agent
por: Tang, Yihong, et al.
Publicado: (2026)

Culture In a Frame: C$^3$B as a Comic-Based Benchmark for Multimodal Culturally Awareness
por: Song, Yuchen, et al.
Publicado: (2025)

Long-form RewardBench: Evaluating Reward Models for Long-form Generation
por: Huang, Hui, et al.
Publicado: (2026)

Dual Instruction Tuning with Large Language Models for Mathematical Reasoning
por: Zhou, Yongwei, et al.
Publicado: (2024)

SAT: Balancing Reasoning Accuracy and Efficiency with Stepwise Adaptive Thinking
por: Huang, Weiyang, et al.
Publicado: (2026)

ResT: Reshaping Token-Level Policy Gradients for Tool-Use Large Language Models
por: Lin, Zihan, et al.
Publicado: (2025)

Character-R1: Enhancing Role-Aware Reasoning in Role-Playing Agents via RLVR
por: Tang, Yihong, et al.
Publicado: (2026)