Imagen de Portada

Sparsity Is Necessary: Polynomial-Time Stability for Agentic LLMs in Large Action Spaces

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Majumdar, Angshul
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Greedy Is Enough: Sparse Action Discovery in Agentic LLMs
por: Majumdar, Angshul
Publicado: (2026)

Near-Optimal Coalition Structures in Polynomial Time
por: Majumdar, Angshul
Publicado: (2025)

The Relativity of AGI: Distributional Axioms, Fragility, and Undecidability
por: Majumdar, Angshul
Publicado: (2026)

The Existential Theory of Research: Why Discovery Is Hard
por: Majumdar, Angshul
Publicado: (2026)

Universal NP-Hardness of Clustering under General Utilities
por: Majumdar, Angshul
Publicado: (2026)

Sparse Probabilistic Coalition Structure Generation: Bayesian Greedy Pursuit and $\ell_1$ Relaxations
por: Majumdar, Angshul
Publicado: (2026)

Bayesian Recovery for Probabilistic Coalition Structures
por: Majumdar, Angshul
Publicado: (2025)

Navigating Extremes: Dynamic Sparsity in Large Output Spaces
por: Ullah, Nasib, et al.
Publicado: (2024)

Real-Time Trust Verification for Safe Agentic Actions using TrustBench
por: Sharma, Tavishi, et al.
Publicado: (2026)

Tensor Spectral Threshold is $\exists\mathbb{R}$-Hard
por: Majumdar, Angshul
Publicado: (2026)

$\exists\mathbb{R}$-Completeness of Tensor Degeneracy and a Derandomization Barrier for Hyperdeterminants
por: Majumdar, Angshul
Publicado: (2026)

Diminishing Returns in Expanding Generative Models and Godel-Tarski-Lob Limits
por: Majumdar, Angshul
Publicado: (2026)

How Hard Is Continuous Clustering? Lower Bounds from the Existential Theory of the Reals
por: Majumdar, Angshul
Publicado: (2026)

Quantum-Compatible Dictionary Learning via Doubly Sparse Models
por: Majumdar, Angshul
Publicado: (2026)

Constrained Nonnegative Gram Feasibility is $\exists\mathbb{R}$-Complete
por: Majumdar, Angshul
Publicado: (2026)

Shannon meets Gödel-Tarski-Löb: Undecidability of Shannon Feedback Capacity for Finite-State Channels
por: Majumdar, Angshul
Publicado: (2026)

Affine Rank Minimization is ER Complete
por: Majumdar, Angshul
Publicado: (2026)

A Unified Matrix Factorization Framework for Classical and Robust Clustering
por: Majumdar, Angshul
Publicado: (2025)

Dictionary-Transform Generative Adversarial Networks
por: Majumdar, Angshul
Publicado: (2025)

Not All Layers of LLMs Are Necessary During Inference
por: Fan, Siqi, et al.
Publicado: (2024)

Structured Agentic Workflows for Financial Time-Series Modeling with LLMs and Reflective Feedback
por: Ang, Yihao, et al.
Publicado: (2025)

Reinforcement Learning With Sparse-Executing Actions via Sparsity Regularization
por: Pang, Jing-Cheng, et al.
Publicado: (2021)

Zeroth-Order Fine-Tuning of LLMs with Extreme Sparsity
por: Guo, Wentao, et al.
Publicado: (2024)

EdgeAIGuard: Agentic LLMs for Minor Protection in Digital Spaces
por: Mujtaba, Ghulam, et al.
Publicado: (2025)

Is PRM Necessary? Problem-Solving RL Implicitly Induces PRM Capability in LLMs
por: Feng, Zhangying, et al.
Publicado: (2025)

Are Rationales Necessary and Sufficient? Tuning LLMs for Explainable Misinformation Detection
por: Wang, Bing, et al.
Publicado: (2026)

PATCH: Learnable Tile-level Hybrid Sparsity for LLMs
por: Hourri, Younes, et al.
Publicado: (2025)

Inference Time Context Sparsity: Illusion or Opportunity?
por: Joshi, Sahil, et al.
Publicado: (2026)

Leave it to the Specialist: Repair Sparse LLMs with Sparse Fine-Tuning via Sparsity Evolution
por: Xiao, Qiao, et al.
Publicado: (2025)

SpeContext: Enabling Efficient Long-context Reasoning with Speculative Context Sparsity in LLMs
por: Xu, Jiaming, et al.
Publicado: (2025)

Position: Agentic Evolution is the Path to Evolving LLMs
por: Lin, Minhua, et al.
Publicado: (2026)

A Survey of Reasoning and Agentic Systems in Time Series with Large Language Models
por: Chang, Ching, et al.
Publicado: (2025)

From Features to Actions: Explainability in Traditional and Agentic AI Systems
por: Chaduvula, Sindhuja, et al.
Publicado: (2026)

The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks
por: Cuadron, Alejandro, et al.
Publicado: (2025)

CHAI for LLMs: Improving Code-Mixed Translation in Large Language Models through Reinforcement Learning with AI Feedback
por: Zhang, Wenbo, et al.
Publicado: (2024)

Steering When Necessary: Flexible Steering Large Language Models with Backtracking
por: Cheng, Zifeng, et al.
Publicado: (2025)

Steklov Activations: Piecewise-Polynomial Gates with Compact Support and Tunable Sparsity
por: Masalskikh, Aleksandr
Publicado: (2026)

Dynamic Neighborhood Construction for Structured Large Discrete Action Spaces
por: Akkerman, Fabian, et al.
Publicado: (2023)

Bayesian Off-Policy Evaluation and Learning for Large Action Spaces
por: Aouali, Imad, et al.
Publicado: (2024)

Towards Agentic Self-Learning LLMs in Search Environment
por: Sun, Wangtao, et al.
Publicado: (2025)