Copertina

Thinking Makes LLM Agents Introverted: How Mandatory Thinking Can Backfire in User-Engaged Agents

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Li, Jiatong, Oh, Changdae, Choi, Hyeong Kyu, Wang, Jindong, Li, Sharon
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

VAUQ: Vision-Aware Uncertainty Quantification for LVLM Self-Evaluation
di: Park, Seongheon, et al.
Pubblicazione: (2026)

Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models?
di: Choi, Hyeong Kyu, et al.
Pubblicazione: (2025)

ModeX: Evaluator-Free Best-of-N Selection for Open-Ended Generation
di: Choi, Hyeong Kyu, et al.
Pubblicazione: (2026)

How Do Transformers Learn to Associate Tokens: Gradient Leading Terms Bring Mechanistic Interpretability
di: Im, Shawn, et al.
Pubblicazione: (2026)

General Exploratory Bonus for Optimistic Exploration in RLHF
di: Li, Wendi, et al.
Pubblicazione: (2025)

When Thinking Backfires: Mechanistic Insights Into Reasoning-Induced Misalignment
di: Yan, Hanqi, et al.
Pubblicazione: (2025)

Conveying Imagistic Thinking in Traditional Chinese Medicine Translation: A Prompt Engineering and LLM-Based Evaluation Framework
di: Han, Jiatong
Pubblicazione: (2025)

Conveying Imagistic Thinking in Traditional Chinese Medicine Translation: A Prompt Engineering and LLM-Based Evaluation Framework
di: Han, Jiatong
Pubblicazione: (2025)

Detecting Distillation Data from Reasoning Models
di: Zhang, Hengxiang, et al.
Pubblicazione: (2025)

PICLe: Eliciting Diverse Behaviors from Large Language Models with Persona In-Context Learning
di: Choi, Hyeong Kyu, et al.
Pubblicazione: (2024)

More Vulnerable than You Think: On the Stability of Tool-Integrated LLM Agents
di: Xiong, Weimin, et al.
Pubblicazione: (2025)

How Well Can LLM Agents Simulate End-User Security and Privacy Attitudes and Behaviors?
di: Li, Yuxuan, et al.
Pubblicazione: (2026)

Your Agent is More Brittle Than You Think: Uncovering Indirect Injection Vulnerabilities in Agentic LLMs
di: Zhu, Wenhui, et al.
Pubblicazione: (2026)

Think Fast and Slow: Step-Level Cognitive Depth Adaptation for LLM Agents
di: Yang, Ruihan, et al.
Pubblicazione: (2026)

MoIN: Mixture of Introvert Experts to Upcycle an LLM
di: Tejankar, Ajinkya, et al.
Pubblicazione: (2024)

Can Thinking Models Think to Detect Hateful Memes?
di: Kmainasi, Mohamed Bayan, et al.
Pubblicazione: (2026)

Beyond One Path: Evaluating and Enhancing Divergent Thinking in Interactive LLM Agents
di: Park, Jihyeong, et al.
Pubblicazione: (2026)

Demystifying Hybrid Thinking: Can LLMs Truly Switch Between Think and No-Think?
di: Wang, Shouren, et al.
Pubblicazione: (2025)

Thinking in a Crowd: How Auxiliary Information Shapes LLM Reasoning
di: Zhao, Haodong, et al.
Pubblicazione: (2025)

Can Machines Think Like Humans? A Behavioral Evaluation of LLM Agents in Dictator Games
di: Ma, Ji
Pubblicazione: (2024)

AdaptThink: Reasoning Models Can Learn When to Think
di: Zhang, Jiajie, et al.
Pubblicazione: (2025)

Language Agents Mirror Human Causal Reasoning Biases. How Can We Help Them Think Like Scientists?
di: GX-Chen, Anthony, et al.
Pubblicazione: (2025)

Think Silently, Think Fast: Dynamic Latent Compression of LLM Reasoning Chains
di: Tan, Wenhui, et al.
Pubblicazione: (2025)

Think Twice: Enhancing LLM Reasoning by Scaling Multi-round Test-time Thinking
di: Tian, Xiaoyu, et al.
Pubblicazione: (2025)

Disagreements in Reasoning: How a Model's Thinking Process Dictates Persuasion in Multi-Agent Systems
di: Zhao, Haodong, et al.
Pubblicazione: (2025)

Thinking in Character: Advancing Role-Playing Agents with Role-Aware Reasoning
di: Tang, Yihong, et al.
Pubblicazione: (2025)

How Contaminated Is Your Benchmark? Quantifying Dataset Leakage in Large Language Models with Kernel Divergence
di: Choi, Hyeong Kyu, et al.
Pubblicazione: (2025)

AgentReview: Exploring Peer Review Dynamics with LLM Agents
di: Jin, Yiqiao, et al.
Pubblicazione: (2024)

Safety-Aware Fine-Tuning of Large Language Models
di: Choi, Hyeong Kyu, et al.
Pubblicazione: (2024)

Symbolic Chain-of-Thought Distillation: Small Models Can Also "Think" Step-by-Step
di: Li, Liunian Harold, et al.
Pubblicazione: (2023)

HeLa-Mem: Hebbian Learning and Associative Memory for LLM Agents
di: Zhu, Jinchang, et al.
Pubblicazione: (2026)

Think-J: Learning to Think for Generative LLM-as-a-Judge
di: Huang, Hui, et al.
Pubblicazione: (2025)

Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate
di: Liang, Tian, et al.
Pubblicazione: (2023)

Visual Instruction Bottleneck Tuning
di: Oh, Changdae, et al.
Pubblicazione: (2025)

Steering LLM Thinking with Budget Guidance
di: Li, Junyan, et al.
Pubblicazione: (2025)

Could Thinking Multilingually Empower LLM Reasoning?
di: Gao, Changjiang, et al.
Pubblicazione: (2025)

Can an Individual Manipulate the Collective Decisions of Multi-Agents?
di: Liu, Fengyuan, et al.
Pubblicazione: (2025)

Beyond Preset Identities: How Agents Form Stances and Boundaries in Generative Societies
di: Zhang, Hanzhong, et al.
Pubblicazione: (2026)

Read More, Think More: Revisiting Observation Reduction for Web Agents
di: Enomoto, Masafumi, et al.
Pubblicazione: (2026)

Can Multimodal Large Language Model Think Analogically?
di: Guo, Diandian, et al.
Pubblicazione: (2024)