Imagen de Portada

D$^2$Evo: Dual Difficulty-Aware Self-Evolution for Data-Efficient Reinforcement Learning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhang, Ru, Li, Renda, Ma, Ziyu, Qiu, Weijie, Tao, Chongyang, Wang, Yong, Chu, Xiangxiang
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Artificial Intelligence Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

AdaCuRL: Adaptive Curriculum Reinforcement Learning with Invalid Sample Mitigation and Historical Revisiting
por: Li, Renda, et al.
Publicado: (2025)

Harder Is Better: Boosting Mathematical Reasoning via Difficulty-Aware GRPO and Multi-Aspect Question Reformulation
por: Dai, Yanqi, et al.
Publicado: (2026)

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

AutoEvoEval: An Automated Framework for Evolving Close-Ended LLM Evaluation Data
por: Wu, JiaRu, et al.
Publicado: (2025)

DISCO Balances the Scales: Adaptive Domain- and Difficulty-Aware Reinforcement Learning on Imbalanced Data
por: Zhou, Yuhang, et al.
Publicado: (2025)

SkillClaw: Let Skills Evolve Collectively with Agentic Evolver
por: Ma, Ziyu, et al.
Publicado: (2026)

Tree Search for LLM Agent Reinforcement Learning
por: Ji, Yuxiang, et al.
Publicado: (2025)

Thinking with Map: Reinforced Parallel Map-Augmented Agent for Geolocalization
por: Ji, Yuxiang, et al.
Publicado: (2026)

Online Difficulty Filtering for Reasoning Oriented Reinforcement Learning
por: Bae, Sanghwan, et al.
Publicado: (2025)

Ace-Skill: Bootstrapping Multimodal Agents with Prioritized and Clustered Evolution
por: Xiong, Feng, et al.
Publicado: (2026)

EvoConfig: Self-Evolving Multi-Agent Systems for Efficient Autonomous Environment Configuration
por: Guo, Xinshuai, et al.
Publicado: (2026)

Where and What Matters: Sensitivity-Aware Task Vectors for Many-Shot Multimodal In-Context Learning
por: Ma, Ziyu, et al.
Publicado: (2025)

EvoTest: Evolutionary Test-Time Learning for Self-Improving Agentic Systems
por: He, Yufei, et al.
Publicado: (2025)

LyriCAR: A Difficulty-Aware Curriculum Reinforcement Learning Framework For Controllable Lyric Translation
por: Ren, Le, et al.
Publicado: (2025)

Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory
por: Wei, Tianxin, et al.
Publicado: (2025)

Make Every Penny Count: Difficulty-Adaptive Self-Consistency for Cost-Efficient Reasoning
por: Wang, Xinglin, et al.
Publicado: (2024)

Self-Harmony: Learning to Harmonize Self-Supervision and Self-Play in Test-Time Reinforcement Learning
por: Wang, Ru, et al.
Publicado: (2025)

Tackling the Inherent Difficulty of Noise Filtering in RAG
por: Liu, Jingyu, et al.
Publicado: (2026)

SeRL: Self-Play Reinforcement Learning for Large Language Models with Limited Data
por: Fang, Wenkai, et al.
Publicado: (2025)

EvoPool: Evolutionary Programmatic Annotation for Label-Efficient Specialized Supervision
por: Xu, Tianyi, et al.
Publicado: (2026)

Interpretable Difficulty-Aware Knowledge Tracing in Tutor-Student Dialogues
por: Huang, Shuyan, et al.
Publicado: (2026)

CogniDual Framework: Self-Training Large Language Models within a Dual-System Theoretical Framework for Improving Cognitive Tasks
por: Deng, Yongxin, et al.
Publicado: (2024)

Playing 20 Question Game with Policy-Based Reinforcement Learning
por: Hu, Huang, et al.
Publicado: (2018)

SeaEvo: Advancing Algorithm Discovery with Strategy Space Evolution
por: Luo, Sichun, et al.
Publicado: (2026)

LaSeR: Reinforcement Learning with Last-Token Self-Rewarding
por: Yang, Wenkai, et al.
Publicado: (2025)

DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving
por: Tong, Yuxuan, et al.
Publicado: (2024)

AdaCtrl: Towards Adaptive and Controllable Reasoning via Difficulty-Aware Budgeting
por: Huang, Shijue, et al.
Publicado: (2025)

EvoSchema: Towards Text-to-SQL Robustness Against Schema Evolution
por: Zhang, Tianshu, et al.
Publicado: (2026)

CoEvolve: Training LLM Agents via Agent-Data Mutual Evolution
por: Yang, Shidong, et al.
Publicado: (2026)

Adaptive Task Balancing for Visual Instruction Tuning via Inter-Task Contribution and Intra-Task Difficulty
por: Dai, Yanqi, et al.
Publicado: (2024)

Enhancing Chemical Reaction and Retrosynthesis Prediction with Large Language Model and Dual-task Learning
por: Lin, Xuan, et al.
Publicado: (2025)

Improving Data Efficiency for LLM Reinforcement Fine-tuning Through Difficulty-targeted Online Data Selection and Rollout Replay
por: Sun, Yifan, et al.
Publicado: (2025)

A Survey on Self-Evolution of Large Language Models
por: Tao, Zhengwei, et al.
Publicado: (2024)

Synthesizing Agentic Data for Web Agents with Progressive Difficulty Enhancement Mechanisms
por: Pandit, Shrey, et al.
Publicado: (2025)

Preference Alignment for Diffusion Model via Explicit Denoised Distribution Estimation
por: Shi, Dingyuan, et al.
Publicado: (2024)

3DS: Medical Domain Adaptation of LLMs via Decomposed Difficulty-based Data Selection
por: Ding, Hongxin, et al.
Publicado: (2024)

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning
por: Zhang, Kongcheng, et al.
Publicado: (2025)

Efficient Task Adaptation in Large Language Models via Selective Parameter Optimization
por: Wan, Weijie, et al.
Publicado: (2026)

RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning
por: Wang, Zihan, et al.
Publicado: (2025)

M-GRPO: Stabilizing Self-Supervised Reinforcement Learning for Large Language Models with Momentum-Anchored Policy Optimization
por: Bai, Bizhe, et al.
Publicado: (2025)