mlsanityData to 14 Oct 2026

Can Induced Emotion Bias LLM Behaviors in Sequential Decision Making?

arXiv 2607.12631 ↗First posted 14 Jul 2026cs.CL cs.AIcited by 0

On the map: LLM agents and tool use → Social simulation and multi-agent debate

Abstract (arXiv)

As Large Language Models (LLMs) are increasingly deployed as autonomous agents in high-stakes domains, understanding contextual factors that may modulate their decision-making becomes critical. While LLMs are trained to perceive and resonate with users' emotions, it remains unclear whether induced emotion can influence their sequential decision-making. We investigate this question using the Iowa Gambling Task (IGT), a classic psychological paradigm for studying decision-making under uncertainty, combined with an imagination-based emotion induction procedure. We first validate the feasibility of this paradigm by confirming that LLMs can sense strong, distinguishable emotions from context and that LLM agents can learn from sequential interactions in a human-like pace. With the validated setup, we find that, different from humans, induced emotion does not significantly bias the decision dynamics of LLM agents on average. However, the effects of anger are conditioned: inducing anger makes LLM agents less sensitive to penalties for bad decisions, and in early stages of the game, anger can lower exploration, locking decisions into a few choices early. These findings reveal the subtle yet distinct effects of induced emotion on LLM decision-making compared to human behavior, and provide a tool for future research on affective modulation of LLM agents.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use. Builds on 31 of its 53 references that are in the map. First posted on arXiv 14 Jul 2026.

Builds on

31 of 53 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Generative Agents: Interactive Simulacra of Human Behavior7 Apr

Other references · 30

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  3. 2025Qwen3 Technical Reportcited by 8,820
  4. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  5. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  6. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,191
  7. 2023Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injectioncited by 1,443
  8. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,439
  9. 2025gpt-oss-120b & gpt-oss-20b Model Cardcited by 1,386
  10. 2023Prompt Injection attack against LLM-integrated Applicationscited by 605
  11. 2025Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAscited by 521
  12. 2023Large Language Models Are Not Robust Multiple Choice Selectorscited by 486
18 more
  1. 2024Agent-SafetyBench: Evaluating the Safety of LLM Agentscited by 306
  2. 2024R-Judge: Benchmarking Safety Risk Awareness for LLM Agentscited by 288
  3. 2023Large Language Models Sensitivity to The Order of Options in Multiple-Choice Questionscited by 263
  4. 2025Evaluation and Benchmarking of LLM Agents: A Surveycited by 152
  5. 2023Large Language Models Understand and Can be Enhanced by Emotional Stimulicited by 146
  6. 2022Thinking Fast and Slow in Large Language Modelscited by 137
  7. 2024Automatic and Universal Prompt Injection Attacks against Large Language Modelscited by 119
  8. 2024CogBench: a large language model walks into a psychology labcited by 63
  9. 2026Emotion Concepts and their Function in a Large Language Modelcited by 57
  10. 2026HEART: A Unified Benchmark for Assessing Humans and LLMs in Emotional Support Dialoguecited by 13
  11. 2023Inducing anxiety in large language models can induce biascited by 10
  12. 2024Towards Next-Generation Medical Agent: How o1 is Reshaping Decision-Making in Medical Scenarioscited by 10
  13. 2025AI shares emotion with humans across languages and culturescited by 6
  14. 2025A Comprehensive Review of AI Agents: Transforming Possibilities in Technology and Beyondcited by 6
  15. 2025Large Language Models are Near-Optimal Decision-Makers with a Non-Human Learning Behaviorcited by 3
  16. 2025LongEmotion: Measuring Emotional Intelligence of Large Language Models in Long-Context Interactioncited by 3
  17. 2025Outraged AI: Large language models prioritise emotion over cost in fairness enforcementcited by 3
  18. 2025Enabling Regulatory Multi-Agent Collaboration: Architecture, Challenges, and Solutionscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Inducing State Anxiety in LLM Agents Reproduces Human-Like Biases in Consumer Decision-Making
  2. 2026On Emotion-Sensitive Decision Making of Small Language Model Agents
  3. 2026Sparks of Rationality: Do Reasoning LLMs Align with Human Judgment and Choice?
  4. 2025LLM Agents Display Human Biases but Exhibit Distinct Learning Patterns
  5. 2024The Good, the Bad, and the Hulk-like GPT: Analyzing Emotional Decisions of Large Language Models in Cooperation and Bargaining Games
  6. 2026Emulating Aggregate Human Choice Behavior and Biases with GPT Conversational Agents
  7. 2025Can Large Language Models Develop Gambling Addiction?
  8. 2024Systematic Biases in LLM Simulations of Debates