Image de couverture de livre

What Do LLM Agents Do When Left Alone? Evidence of Spontaneous Meta-Cognitive Patterns

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Szeider, Stefan
Format:	Preprint
Publié:	2025
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

LLM Self-Explanations Fail Semantic Invariance
par: Szeider, Stefan
Publié: (2026)

CP-Agent: Agentic Constraint Programming
par: Szeider, Stefan
Publié: (2025)

PBLean: Pseudo-Boolean Proof Certificates for Lean 4
par: Szeider, Stefan
Publié: (2026)

Algorithm Selection with Zero Domain Knowledge via Text Embeddings
par: Szeider, Stefan
Publié: (2026)

ASP-Bench: From Natural Language to Logic Programs
par: Szeider, Stefan
Publié: (2026)

Doing What They Say, Not What They Reason: Locating the Faithfulness Gap in LLM Agents
par: Wang, Yufeng
Publié: (2026)

Do Proactive Agents Really Need an LLM to Decide When to Wake and What to Anchor?
par: Liu, Xiaoze, et autres
Publié: (2026)

MCP-Solver: Integrating Language Models with Constraint Programming Systems
par: Szeider, Stefan
Publié: (2024)

Extracting Problem Structure with LLMs for Optimized SAT Local Search
par: Schidler, André, et autres
Publié: (2025)

Do Agents Know What They Can't Do? Evaluating Feasibility Awareness in Tool-Using Agents
par: Cheng, Liang, et autres
Publié: (2026)

When Do LLM Preferences Predict Downstream Behavior?
par: Slama, Katarina, et autres
Publié: (2026)

Why Do Multi-Agent LLM Systems Fail?
par: Cemri, Mert, et autres
Publié: (2025)

Do Cognitively Interpretable Reasoning Traces Improve LLM Performance?
par: Bhambri, Siddhant, et autres
Publié: (2025)

Do Agent Societies Develop Intellectual Elites? The Hidden Power Laws of Collective Cognition in LLM Multi-Agent Systems
par: Venkatesh, Kavana, et autres
Publié: (2026)

Do Role-Playing Agents Practice What They Preach? Belief-Behavior Consistency in LLM-Based Simulations of Human Trust
par: Mannekote, Amogh, et autres
Publié: (2025)

What Do LLM Agents Know About Their World? Task2Quiz: A Paradigm for Studying Environment Understanding
par: Liu, Siyuan, et autres
Publié: (2026)

Explaining Decisions in ML Models: a Parameterized Complexity Analysis (Part I)
par: Ordyniak, Sebastian, et autres
Publié: (2025)

Smart Cubing for Graph Search: A Comparative Study
par: Kirchweger, Markus, et autres
Publié: (2025)

When Agents Overtrust Environmental Evidence: An Extensible Agentic Framework for Benchmarking Evidence-Grounding Defects in LLM Agents
par: Sheng, Strick, et autres
Publié: (2026)

What Can You Do When You Have Zero Rewards During RL?
par: Prakash, Jatin, et autres
Publié: (2025)

Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations
par: Hoang, Huy, et autres
Publié: (2025)

When Agents Say One Thing and Do Another: Validating Elicited Beliefs from LLMs
par: Yamin, Khurram, et autres
Publié: (2026)

When Robots Do the Chores: A Benchmark and Agent for Long-Horizon Household Task Execution
par: Zhu, Zilin, et autres
Publié: (2026)

HiL-Bench (Human-in-Loop Benchmark): Do Agents Know When to Ask for Help?
par: Trinh, Tu, et autres
Publié: (2026)

What Would an LLM Do? Evaluating Large Language Models for Policymaking to Alleviate Homelessness
par: Coz, Pierre Le, et autres
Publié: (2025)

Do Large Language Models Mentalize When They Teach?
par: Harootonian, Sevan K., et autres
Publié: (2026)

When Do Multi-Agent Systems Outperform? Analysing the Learning Efficiency of Agentic Systems
par: Su, Junwei, et autres
Publié: (2026)

Explaining Decisions in ML Models: a Parameterized Complexity Analysis
par: Ordyniak, Sebastian, et autres
Publié: (2024)

Do LLM Agents Exhibit Social Behavior?
par: Leng, Yan, et autres
Publié: (2023)

FormGym: Doing Paperwork with Agents
par: Toles, Matthew, et autres
Publié: (2025)

What Is AI Safety? What Do We Want It to Be?
par: Harding, Jacqueline, et autres
Publié: (2025)

Generating Streamlining Constraints with Large Language Models
par: Voboril, Florentina, et autres
Publié: (2024)

Do LLMs Capture Embodied Cognition and Cultural Variation? Cross-Linguistic Evidence from Demonstratives
par: Wang, Yu, et autres
Publié: (2026)

What Do Learned Models Measure?
par: Žliobaitė, Indrė
Publié: (2026)

When Models Know When They Do Not Know: Calibration, Cascading, and Cleaning
par: Hao, Chenjie, et autres
Publié: (2026)

Applying Cognitive Design Patterns to General LLM Agents
par: Wray, Robert E., et autres
Publié: (2025)

Do Code LLMs Understand Design Patterns?
par: Pan, Zhenyu, et autres
Publié: (2025)

Streamliners for Answer Set Programming
par: Voboril, Florentina, et autres
Publié: (2026)

Compilation and Fast Model Counting beyond CNF
par: de Colnet, Alexis, et autres
Publié: (2025)

Do Self-Evolving Agents Forget? Capability Degradation and Preservation in Lifelong LLM Agent Adaptation
par: Yu, Ye, et autres
Publié: (2026)