Imagen de Portada

Disagreement as Data: Reasoning Trace Analytics in Multi-Agent Systems

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Tajik, Elham, Borchers, Conrad, Shahrokhian, Bahar, Simon, Sebastian, Keramati, Ali, Pal, Sonika, Sankaranarayanan, Sreecharan
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Temperature and Persona Shape LLM Agent Consensus With Minimal Accuracy Gains in Qualitative Coding
por: Borchers, Conrad, et al.
Publicado: (2025)

Mitigating "Epistemic Debt" in Generative AI-Scaffolded Novice Programming using Metacognitive Scripts
por: Sankaranarayanan, Sreecharan
Publicado: (2026)

Can Large Language Models Match Tutoring System Adaptivity? A Benchmarking Study
por: Borchers, Conrad, et al.
Publicado: (2025)

Parametric Constraints for Bayesian Knowledge Tracing from First Principles
por: Shchepakin, Denis, et al.
Publicado: (2023)

Disentangling Learning from Judgment: Representation Learning for Open Response Analytics
por: Borchers, Conrad, et al.
Publicado: (2025)

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

Benchmarking Educational LLMs with Analytics: A Case Study on Gender Bias in Feedback
por: Du, Yishan, et al.
Publicado: (2025)

DART: Leveraging Multi-Agent Disagreement for Tool Recruitment in Multimodal Reasoning
por: Sivakumaran, Nithin, et al.
Publicado: (2025)

Representation Learning to Study Temporal Dynamics in Tutorial Scaffolding
por: Borchers, Conrad, et al.
Publicado: (2026)

When Disagreements Elicit Robustness: Investigating Self-Repair Capabilities under LLM Multi-Agent Disagreements
por: Ju, Tianjie, et al.
Publicado: (2025)

Large Language Models as Students Who Think Aloud: Overly Coherent, Verbose, and Confident
por: Borchers, Conrad, et al.
Publicado: (2026)

Physiological and Semantic Patterns in Medical Teams Using an Intelligent Tutoring System
por: Huang, Xiaoshan, et al.
Publicado: (2026)

The Hidden Strength of Disagreement: Unraveling the Consensus-Diversity Tradeoff in Adaptive Multi-Agent Systems
por: Wu, Zengqing, et al.
Publicado: (2025)

Augmenting Human-Annotated Training Data with Large Language Model Generation and Distillation in Open-Response Assessment
por: Borchers, Conrad, et al.
Publicado: (2025)

AgentAda: Skill-Adaptive Data Analytics for Tailored Insight Discovery
por: Abaskohi, Amirhossein, et al.
Publicado: (2025)

Toward Trait-Aware Learning Analytics
por: Borchers, Conrad, et al.
Publicado: (2026)

MSA at BEA 2025 Shared Task: Disagreement-Aware Instruction Tuning for Multi-Dimensional Evaluation of LLMs as Math Tutors
por: Hikal, Baraa, et al.
Publicado: (2025)

Reinforcement Learning for LLM-based Multi-Agent Systems through Orchestration Traces
por: Zhang, Chenchen
Publicado: (2026)

Understanding Teacher Revisions of Large Language Model-Generated Feedback
por: Borchers, Conrad, et al.
Publicado: (2026)

Can Reasoning Help Large Language Models Capture Human Annotator Disagreement?
por: Ni, Jingwei, et al.
Publicado: (2025)

Leveraging Annotator Disagreement for Text Classification
por: Xu, Jin, et al.
Publicado: (2024)

LLM-Generated Feedback Supports Learning If Learners Choose to Use It
por: Thomas, Danielle R., et al.
Publicado: (2025)

G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems
por: Zhang, Guibin, et al.
Publicado: (2025)

DiscoUQ: Structured Disagreement Analysis for Uncertainty Quantification in LLM Agent Ensembles
por: Jiang, Bo
Publicado: (2026)

D3CODE: Disentangling Disagreements in Data across Cultures on Offensiveness Detection and Evaluation
por: Davani, Aida Mostafazadeh, et al.
Publicado: (2024)

Quantifying and Predicting Disagreement in Graded Human Ratings
por: Zhang, Leixin, et al.
Publicado: (2026)

From Tokens to Steps: Verification-Aware Speculative Decoding for Efficient Multi-Step Reasoning
por: Purohit, Kiran, et al.
Publicado: (2026)

TraceBack: Multi-Agent Decomposition for Fine-Grained Table Attribution
por: Anvekar, Tejas, et al.
Publicado: (2026)

Aligning LLM Uncertainty with Human Disagreement in Subjectivity Analysis
por: Lu, Junyu, et al.
Publicado: (2026)

NUTMEG: Separating Signal From Noise in Annotator Disagreement
por: Ivey, Jonathan, et al.
Publicado: (2025)

Do Differences in Values Influence Disagreements in Online Discussions?
por: van der Meer, Michiel, et al.
Publicado: (2023)

Bridging the Gap: In-Context Learning for Modeling Human Disagreement
por: Muscato, Benedetta, et al.
Publicado: (2025)

From Disagreement to Understanding: The Case for Ambiguity Detection in NLI
por: Jayaweera, Chathuri, et al.
Publicado: (2025)

CogniAlign: Survivability-Grounded Multi-Agent Moral Reasoning for Safe and Transparent AI
por: Ali, Hasin Jawad, et al.
Publicado: (2025)

ReasoningFlow: Semantic Structure of Complex Reasoning Traces
por: Lee, Jinu, et al.
Publicado: (2025)

MASLegalBench: Benchmarking Multi-Agent Systems in Deductive Legal Reasoning
por: Jing, Huihao, et al.
Publicado: (2025)

Learning to Break: Knowledge-Enhanced Reasoning in Multi-Agent Debate System
por: Wang, Haotian, et al.
Publicado: (2023)

TraceSIR: A Multi-Agent Framework for Structured Analysis and Reporting of Agentic Execution Traces
por: Yang, Shu-Xun, et al.
Publicado: (2026)

Insight Agents: An LLM-Based Multi-Agent System for Data Insights
por: Bai, Jincheng, et al.
Publicado: (2026)

Beyond Consensus: Perspectivist Modeling and Evaluation of Annotator Disagreement in NLP
por: Xu, Yinuo, et al.
Publicado: (2026)