Image de couverture de livre

Greedy Is Enough: Sparse Action Discovery in Agentic LLMs

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Majumdar, Angshul
Format:	Preprint
Publié:	2026
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Sparsity Is Necessary: Polynomial-Time Stability for Agentic LLMs in Large Action Spaces
par: Majumdar, Angshul
Publié: (2026)

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

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

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

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

Near-Optimal Coalition Structures in Polynomial Time
par: Majumdar, Angshul
Publié: (2025)

Bayesian Recovery for Probabilistic Coalition Structures
par: Majumdar, Angshul
Publié: (2025)

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

Grounding LLMs in Scientific Discovery via Embodied Actions
par: Zhang, Bo, et autres
Publié: (2026)

QV May Be Enough: Toward the Essence of Attention in LLMs
par: Edward, Zhang
Publié: (2026)

Benchmarks are Not Enough: RAMP for Runtime Assessing of Agentic Models in Production Systems
par: Ouyang, Yipeng, et autres
Publié: (2026)

Fitting Is Not Enough: Smoothness in Extremely Quantized LLMs
par: Xu, Yuzhuang, et autres
Publié: (2026)

Greedy Output Approximation: Towards Efficient Structured Pruning for LLMs Without Retraining
par: Li, Jianwei, et autres
Publié: (2024)

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

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

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

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

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

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

Affine Rank Minimization is ER Complete
par: Majumdar, Angshul
Publié: (2026)

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

Dictionary-Transform Generative Adversarial Networks
par: Majumdar, Angshul
Publié: (2025)

Agentic Skill Discovery
par: Zhao, Xufeng, et autres
Publié: (2024)

The Good, The Bad, and The Greedy: Evaluation of LLMs Should Not Ignore Non-Determinism
par: Song, Yifan, et autres
Publié: (2024)

Reward Is Enough: LLMs Are In-Context Reinforcement Learners
par: Song, Kefan, et autres
Publié: (2025)

Reasoning Isn't Enough: Examining Truth-Bias and Sycophancy in LLMs
par: Barkett, Emilio, et autres
Publié: (2025)

Agentic AI Scientists Are Not Built For Autonomous Scientific Discovery
par: Bisht, Harshit, et autres
Publié: (2026)

SR-Scientist: Scientific Equation Discovery With Agentic AI
par: Xia, Shijie, et autres
Publié: (2025)

LLMs are Greedy Agents: Effects of RL Fine-tuning on Decision-Making Abilities
par: Schmied, Thomas, et autres
Publié: (2025)

Sparse is Enough in Fine-tuning Pre-trained Large Language Models
par: Song, Weixi, et autres
Publié: (2023)

Embodied Science: Closing the Discovery Loop with Agentic Embodied AI
par: Zhuang, Xiang, et autres
Publié: (2026)

ATLAS: Agentic or Latent Visual Reasoning? One Word is Enough for Both
par: Guo, Ziyu, et autres
Publié: (2026)

Position: Agentic Evolution is the Path to Evolving LLMs
par: Lin, Minhua, et autres
Publié: (2026)

Agentic Discovery of Exchange-Correlation Density Functionals
par: Duston, Titouan, et autres
Publié: (2026)

Agentic Discovery: Closing the Loop with Cooperative Agents
par: Pauloski, J. Gregory, et autres
Publié: (2025)

From Features to Actions: Explainability in Traditional and Agentic AI Systems
par: Chaduvula, Sindhuja, et autres
Publié: (2026)

The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks
par: Cuadron, Alejandro, et autres
Publié: (2025)

When Is Enough Not Enough? Illusory Completion in Search Agents
par: Ko, Dayoon, et autres
Publié: (2026)

DemoEvolve: Overcoming Sparse Feedback in Agentic Harness Evolution with Demonstrations
par: Che, Lirong, et autres
Publié: (2026)

PolitNuggets: Benchmarking Agentic Discovery of Long-Tail Political Facts
par: Zhu, Yifei
Publié: (2026)