mlsanityData to 14 Oct 2026

HEART: Emotionally-Driven Test-Time Scaling of Language Models

arXiv 2509.22876 ↗First posted 26 Sep 2025cs.CL cs.LGcited by 0

On the map: LLM reasoning → Audio-language model reasoning

Abstract (arXiv)

Test-time scaling has significantly improved how AI models solve problems, yet current methods often get stuck in repetitive, incorrect patterns of thought. We introduce HEART, a framework that uses emotional cues to guide the model's focus, much like how feelings contribute to human decision-making. By alternating between critical tones to sharpen error detection and encouraging tones to spark new ideas, HEART helps the model break out of dead-end reasoning and find the right solution. We evaluate HEART across seven high-difficulty benchmarks--including Humanity's Last Exam, GPQA Diamond, and LiveCodeBench--demonstrating robustness across diverse models. Results show that emotion facilitates deeper reasoning, yielding consistent accuracy gains over affect-sterile baselines. These findings suggest that the next frontier in machine reasoning lies in the strategic integration of affective regulation to guide logical synthesis.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Audio-language model reasoning, one of 17 directions in LLM reasoning. Builds on 31 of its 43 references that are in the map. First posted on arXiv 26 Sep 2025.

Builds on

31 of 43 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Enhancing Emotional Generation Capability of Large Language Models via Emotional Chain-of-Thought12 Jan

Other references · 30

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  2. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  3. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  4. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,796
  5. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  6. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  7. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,879
  8. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Codecited by 2,004
  9. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameterscited by 1,986
  10. 2022Language Models (Mostly) Know What They Knowcited by 1,856
  11. 2025Gemma 3 Technical Reportcited by 1,824
  12. 2025s1: Simple test-time scalingcited by 1,341
18 more
  1. 2024OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problemscited by 1,136
  2. 2023Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Promptingcited by 1,122
  3. 2023Towards Understanding Sycophancy in Language Modelscited by 1,040
  4. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 1,017
  5. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Modelscited by 886
  6. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquingcited by 783
  7. 2023Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Modelscited by 574
  8. 2024Measuring short-form factuality in large language modelscited by 373
  9. 2022Generating Sequences by Learning to Self-Correctcited by 277
  10. 2024When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMscited by 240
  11. 2023Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategiescited by 238
  12. 2023Large Language Models Understand and Can be Enhanced by Emotional Stimulicited by 146
  13. 2022Faithful Reasoning Using Large Language Modelscited by 130
  14. 2023System 2 Attention (is something you might need too)cited by 89
  15. 2023Emotional Intelligence of Large Language Modelscited by 58
  16. 2025SimpleQA Verified: A Reliable Factuality Benchmark to Measure Parametric Knowledgecited by 54
  17. 2023A Closer Look at the Self-Verification Abilities of Large Language Models in Logical Reasoningcited by 41
  18. 2025SLOT: Sample-specific Language Model Optimization at Test-timecited by 18

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026From Emotion Classification to Emotional Reasoning: Enhancing Emotional Intelligence in Large Language Models
  2. 2026Unveiling the Cognitive Compass: Theory-of-Mind-Guided Multimodal Emotion Reasoning
  3. 2025Sentient Agent as a Judge: Evaluating Higher-Order Social Cognition in Large Language Models
  4. 2025The Personalization Trap: How User Memory Alters Emotional Reasoning in LLMs
  5. 2023MindGames: Targeting Theory of Mind in Large Language Models with Dynamic Epistemic Modal Logic
  6. 2023FANToM: A Benchmark for Stress-testing Machine Theory of Mind in Interactions
  7. 2025Large language models show fragile cognitive reasoning about human emotions
  8. 2026Do Emotions in Prompts Matter? Effects of Emotional Framing on Large Language Models