:: Library Catalog

Copertina

Salvato in:

Dettagli Bibliografici
Autori principali:	Ai, Zhengyang, Shan, Zikang, Ai, Xiaodong, Tang, Jingxian, Hu, Hangkai, Lu, Pinyan
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Artificial Intelligence Computation and Language
Accesso online:	https://arxiv.org/abs/2604.06636
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Bringing Value Models Back: Generative Critics for Value Modeling in LLM Reinforcement Learning
di: Shan, Zikang, et al.
Pubblicazione: (2026)

Revisiting Entropy Regularization: Adaptive Coefficient Unlocks Its Potential for LLM Reinforcement Learning
di: Zhang, Xiaoyun, et al.
Pubblicazione: (2025)

Arbitrage: Efficient Reasoning via Advantage-Aware Speculation
di: Maheswaran, Monishwaran, et al.
Pubblicazione: (2025)

ReasonFlux: Hierarchical LLM Reasoning via Scaling Thought Templates
di: Yang, Ling, et al.
Pubblicazione: (2025)

MathScale: Scaling Instruction Tuning for Mathematical Reasoning
di: Tang, Zhengyang, et al.
Pubblicazione: (2024)

Less is More: Improving LLM Alignment via Preference Data Selection
di: Deng, Xun, et al.
Pubblicazione: (2025)

Efficient Long-distance Latent Relation-aware Graph Neural Network for Multi-modal Emotion Recognition in Conversations
di: Shou, Yuntao, et al.
Pubblicazione: (2024)

Logical Structure as Knowledge: Enhancing LLM Reasoning via Structured Logical Knowledge Density Estimation
di: Bi, Zhen, et al.
Pubblicazione: (2025)

GEAR: Granularity-Adaptive Advantage Reweighting for LLM Agents via Self-Distillation
di: Li, Sijia, et al.
Pubblicazione: (2026)

Unveiling Memorization-Generalization Coexistence: A Case Study on Arithmetic Tasks with Label Noise
di: Liu, Linyu, et al.
Pubblicazione: (2026)

HS-STaR: Hierarchical Sampling for Self-Taught Reasoners via Difficulty Estimation and Budget Reallocation
di: Xiong, Feng, et al.
Pubblicazione: (2025)

Quantile Advantage Estimation: Stabilizing RLVR for LLM Reasoning
di: Wu, Junkang, et al.
Pubblicazione: (2025)

Blockwise Advantage Estimation for Multi-Objective RL with Verifiable Rewards
di: Pavlenko, Kirill, et al.
Pubblicazione: (2026)

RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic Sampling
di: Liu, Yang, et al.
Pubblicazione: (2025)

How Numerical Precision Affects Arithmetical Reasoning Capabilities of LLMs
di: Feng, Guhao, et al.
Pubblicazione: (2024)

Graph Counselor: Adaptive Graph Exploration via Multi-Agent Synergy to Enhance LLM Reasoning
di: Gao, Junqi, et al.
Pubblicazione: (2025)

No Prompt Left Behind: Exploiting Zero-Variance Prompts in LLM Reinforcement Learning via Entropy-Guided Advantage Shaping
di: Le, Thanh-Long V., et al.
Pubblicazione: (2025)

Option-ID Based Elimination For Multiple Choice Questions
di: Zhu, Zhenhao, et al.
Pubblicazione: (2025)

Better LLM Reasoning via Dual-Play
di: Zhang, Zhengxin, et al.
Pubblicazione: (2025)

CoRT: Code-integrated Reasoning within Thinking
di: Li, Chengpeng, et al.
Pubblicazione: (2025)

GIFT: Reconciling Post-Training Objectives via Finite-Temperature Gibbs Initialization
di: Zhao, Zhengyang, et al.
Pubblicazione: (2026)

MixAtlas: Uncertainty-aware Data Mixture Optimization for Multimodal LLM Midtraining
di: Wen, Bingbing, et al.
Pubblicazione: (2026)

Mitigating Reward Hacking in RLHF via Advantage Sign Robustness
di: Ono, Shinnosuke, et al.
Pubblicazione: (2026)

Tree-OPO: Off-policy Monte Carlo Tree-Guided Advantage Optimization for Multistep Reasoning
di: Huang, Bingning, et al.
Pubblicazione: (2025)

Advancing LLM Reasoning Generalists with Preference Trees
di: Yuan, Lifan, et al.
Pubblicazione: (2024)

Conditional Advantage Estimation for Reinforcement Learning in Large Reasoning Models
di: Chen, Guanxu, et al.
Pubblicazione: (2025)

RelayLLM: Efficient Reasoning via Collaborative Decoding
di: Huang, Chengsong, et al.
Pubblicazione: (2026)

From Reasoning Chains to Verifiable Subproblems: Curriculum Reinforcement Learning Enables Credit Assignment for LLM Reasoning
di: Jiang, Xitai, et al.
Pubblicazione: (2026)

Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning Capability
di: Lin, Zicheng, et al.
Pubblicazione: (2024)

FlowRL: Matching Reward Distributions for LLM Reasoning
di: Zhu, Xuekai, et al.
Pubblicazione: (2025)

What Scales in Cross-Entropy Scaling Law?
di: Yan, Junxi, et al.
Pubblicazione: (2025)

Safe: Enhancing Mathematical Reasoning in Large Language Models via Retrospective Step-aware Formal Verification
di: Liu, Chengwu, et al.
Pubblicazione: (2025)

Internalizing LLM Reasoning via Discovery and Replay of Latent Actions
di: Shi, Zhenning, et al.
Pubblicazione: (2026)

Assessing LLM Reasoning Steps via Principal Knowledge Grounding
di: Hwang, Hyeon, et al.
Pubblicazione: (2025)

Stable Adaptive Thinking via Advantage Shaping and Length-Aware Gradient Regulation
di: Xu, Zihang, et al.
Pubblicazione: (2026)

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision
di: Xi, Zhiheng, et al.
Pubblicazione: (2024)

CosmicFish-HRM: Adaptive Reasoning via Hierarchical Recurrent Mechanisms in Compact Language Models
di: Lakkapragada, Venkat Akhil
Pubblicazione: (2026)

GraphDancer: Training LLMs to Explore and Reason over Graphs via Two-Stage Curriculum Post-Training
di: Bai, Yuyang, et al.
Pubblicazione: (2026)

ReasonBENCH: Benchmarking the (In)Stability of LLM Reasoning
di: Potamitis, Nearchos, et al.
Pubblicazione: (2025)

DRAGON: Guard LLM Unlearning in Context via Negative Detection and Reasoning
di: Wang, Yaxuan, et al.
Pubblicazione: (2025)