Cover Image

Evolutionary Task Discovery: Advancing Reasoning Frontiers via Skill Composition and Complexity Scaling

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ye, Liqin, Yin, Yanbin, Galarnyk, Michael, Heng, Yuzhao, Chava, Sudheer, Zhang, Chao
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Precise Attribute Intensity Control in Large Language Models via Targeted Representation Editing
by: Zhang, Rongzhi, et al.
Published: (2025)

Calibrating Pre-trained Language Classifiers on LLM-generated Noisy Labels via Iterative Refinement
by: Ye, Liqin, et al.
Published: (2025)

IPO-Mine: A Toolkit and Dataset for Section-Structured Analysis of Long, Multimodal IPO Documents
by: Galarnyk, Michael, et al.
Published: (2026)

ConfReady: A RAG based Assistant and Dataset for Conference Checklist Responses
by: Galarnyk, Michael, et al.
Published: (2024)

VideoConviction: A Multimodal Benchmark for Human Conviction and Stock Market Recommendations
by: Galarnyk, Michael, et al.
Published: (2025)

Financial Instruction Following Evaluation (FIFE)
by: Matlin, Glenn, et al.
Published: (2025)

Laying the Foundation First? Investigating the Generalization from Atomic Skills to Complex Reasoning Tasks
by: Huang, Yuncheng, et al.
Published: (2024)

Frontier LLMs Still Struggle with Simple Reasoning Tasks
by: Malek, Alan, et al.
Published: (2025)

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

Beyond Shallow Behavior: Task-Efficient Value-Based Multi-Task Offline MARL via Skill Discovery
by: Wang, Xun, et al.
Published: (2025)

Subgoal Search For Complex Reasoning Tasks
by: Czechowski, Konrad, et al.
Published: (2021)

Unsupervised Skill Discovery for Robotic Manipulation through Automatic Task Generation
by: Jansonnie, Paul, et al.
Published: (2024)

SafeRedirect: Defeating Internal Safety Collapse via Task-Completion Redirection in Frontier LLMs
by: Pan, Chao, et al.
Published: (2026)

Efficient Skill Discovery via Regret-Aware Optimization
by: Zhang, He, et al.
Published: (2025)

Evolutionary Discovery of Reinforcement Learning Algorithms via Large Language Models
by: Sygkounas, Alkis, et al.
Published: (2026)

Reference Grounded Skill Discovery
by: Rho, Seungeun, et al.
Published: (2025)

Agentic Skill Discovery
by: Zhao, Xufeng, et al.
Published: (2024)

Diffusion Meets Options: Hierarchical Generative Skill Composition for Temporally-Extended Tasks
by: Feng, Zeyu, et al.
Published: (2024)

AceMath: Advancing Frontier Math Reasoning with Post-Training and Reward Modeling
by: Liu, Zihan, et al.
Published: (2024)

How Inclusively do LMs Perceive Social and Moral Norms?
by: Galarnyk, Michael, et al.
Published: (2025)

FiNER-ORD: Financial Named Entity Recognition Open Research Dataset
by: Shah, Agam, et al.
Published: (2023)

Compute Optimal Scaling of Skills: Knowledge vs Reasoning
by: Roberts, Nicholas, et al.
Published: (2025)

Effective Frontiers: A Unification of Neural Scaling Laws
by: Zou, Jiaxuan, et al.
Published: (2026)

FlipVQA: Scaling Multi-modal Instruction Tuning via Textbook-to-Knowledge Synthesis
by: Wong, Zhen Hao, et al.
Published: (2025)

Variational Offline Multi-agent Skill Discovery
by: Chen, Jiayu, et al.
Published: (2024)

Efficient Embedding-based Synthetic Data Generation for Complex Reasoning Tasks
by: Jayaraman, Srideepika, et al.
Published: (2026)

Compositional Generalization from Learned Skills via CoT Training: A Theoretical and Structural Analysis for Reasoning
by: Yao, Xinhao, et al.
Published: (2025)

Learning to Reason at the Frontier of Learnability
by: Foster, Thomas, et al.
Published: (2025)

Leveraging Human Feedback for Semantically-Relevant Skill Discovery
by: Hussonnois, Maxence, et al.
Published: (2026)

ScaleDiff: Scaling Difficult Problems for Advanced Mathematical Reasoning
by: Pei, Qizhi, et al.
Published: (2025)

Lightweight MSA Design Advances Protein Folding From Evolutionary Embeddings
by: Cao, Hanqun, et al.
Published: (2025)

Evaluation-driven Scaling for Scientific Discovery
by: Ye, Haotian, et al.
Published: (2026)

SUSD: Structured Unsupervised Skill Discovery through State Factorization
by: Hosseini, Seyed Mohammad Hadi, et al.
Published: (2026)

Skill-Based Mixture-of-Experts: Adaptive Routing for Heterogeneous Reasoning via Inferred Skills
by: Chen, Justin Chih-Yao, et al.
Published: (2025)

Language Guided Skill Discovery
by: Rho, Seungeun, et al.
Published: (2024)

CauScale: Neural Causal Discovery at Scale
by: Peng, Bo, et al.
Published: (2026)

Task Agnostic Architecture for Algorithm Induction via Implicit Composition
by: Sindhi, Sahil J., et al.
Published: (2024)

Skillful Kilometer-Scale Regional Weather Forecasting via Global and Regional Coupling
by: Chen, Weiqi, et al.
Published: (2026)

Procedural Generation of Algorithm Discovery Tasks in Machine Learning
by: Goldie, Alexander D., et al.
Published: (2026)

Advancing Compositional LLM Reasoning with Structured Task Relations in Interactive Multimodal Communications
by: Cao, Xinye, et al.
Published: (2025)