Cover Image

The Observability Gap: Why Output-Level Human Feedback Fails for LLM Coding Agents

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Yinghao, Wang, Cheng
Format:	Preprint
Published:	2026
Subjects:	Human-Computer Interaction
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

SPHERE: Scaling Personalized Feedback in Programming Classrooms with Structured Review of LLM Outputs
by: Tang, Xiaohang, et al.
Published: (2024)

Why Someone Asked "Why": Foil Inference in Human and LLM Question Interpretation
by: Besch, Britt, et al.
Published: (2026)

Who Fails Where? LLM and Human Error Patterns in Endometriosis Ultrasound Report Extraction
by: Li, Haiyi, et al.
Published: (2026)

Would You Like to Visit My World? Cultivating Perceived Equality in Human-Agent Interaction via Observable Social Life Spaces
by: He, Zihong, et al.
Published: (2026)

From Human-Human Collaboration to Human-Agent Collaboration: A Vision, Design Philosophy, and an Empirical Framework for Achieving Successful Partnerships Between Humans and LLM Agents
by: Yao, Bingsheng, et al.
Published: (2026)

Adanonymizer: Interactively Navigating and Balancing the Duality of Privacy and Output Performance in Human-LLM Interaction
by: Zhang, Shuning, et al.
Published: (2024)

Why Report Failed Interactions With Robots?! Towards Vignette-based Interaction Quality
by: Axelsson, Agnes, et al.
Published: (2025)

ViviDoc: Generating Interactive Documents through Human-Agent Collaboration
by: Tang, Yinghao, et al.
Published: (2026)

From Tool to Teammate: LLM Coding Agents as Collaborative Partners for Behavioral Labeling in Educational Dialogue Analysis
by: Chen, Eason, et al.
Published: (2026)

InterLink: Linking Text with Code and Output in Computational Notebooks
by: Lin, Yanna, et al.
Published: (2025)

Who Validates the Validators? Aligning LLM-Assisted Evaluation of LLM Outputs with Human Preferences
by: Shankar, Shreya, et al.
Published: (2024)

The Perceptual Gap: Why We Need Accessible XAI for Assistive Technologies
by: Choudhury, Shadab H.
Published: (2026)

How do Observable Users Decompose D3 Code? A Qualitative Study
by: Lin, Melissa, et al.
Published: (2024)

Limitations of the LLM-as-a-Judge Approach for Evaluating LLM Outputs in Expert Knowledge Tasks
by: Szymanski, Annalisa, et al.
Published: (2024)

Feedback by Design: Understanding and Overcoming User Feedback Barriers in Conversational Agents
by: Sharma, Nikhil, et al.
Published: (2026)

DxHF: Providing High-Quality Human Feedback for LLM Alignment via Interactive Decomposition
by: Shi, Danqing, et al.
Published: (2025)

Sketch Then Generate: Providing Incremental User Feedback and Guiding LLM Code Generation through Language-Oriented Code Sketches
by: Zhu-Tian, Chen, et al.
Published: (2024)

The Persuasion Paradox: When LLM Explanations Fail to Improve Human-AI Team Performance
by: Cohen, Ruth, et al.
Published: (2026)

Can LLM-Simulated Practice and Feedback Upskill Human Counselors? A Randomized Study with 90+ Novice Counselors
by: Louie, Ryan, et al.
Published: (2025)

Inferring Belief States in Partially-Observable Human-Robot Teams
by: Kolb, Jack, et al.
Published: (2024)

Human-Centered LLM-Agent User Interface: A Position Paper
by: Chin, Daniel, et al.
Published: (2024)

A Comprehensive Survey of Electrical Stimulation Haptic Feedback in Human-Computer Interaction
by: Yang, Simin, et al.
Published: (2025)

The Behavioral Fabric of LLM-Powered GUI Agents: Human Values and Interaction Outcomes
by: Gebreegziabher, Simret Araya, et al.
Published: (2026)

What is (H)CI: Why Does the "Human'' Matter?
by: Agarwal, Sejal, et al.
Published: (2026)

WaitGPT: Monitoring and Steering Conversational LLM Agent in Data Analysis with On-the-Fly Code Visualization
by: Xie, Liwenhan, et al.
Published: (2024)

Zoomable Level-of-Detail ChartTables for Interpreting Probabilistic Model Outputs for Reactionary Train Delays
by: Slingsby, Aidan, et al.
Published: (2024)

From First Draft to Final Insight: A Multi-Agent Approach for Feedback Generation
by: Cao, Jie, et al.
Published: (2025)

Same Feedback, Different Source: How AI vs. Human Feedback Shapes Learner Engagement
by: Morris, Caitlin, et al.
Published: (2026)

Hedwig: Dynamic Autonomy for Coding Agents Under Local Oversight
by: Shukla, Tanjal, et al.
Published: (2026)

Zara: An LLM-based Candidate Interview Feedback System
by: Yazdani, Nima, et al.
Published: (2025)

Facilitating Human Feedback for GenAI Prompt Optimization
by: Sherson, Jacob, et al.
Published: (2024)

When Benchmarks Talk: Re-Evaluating Code LLMs with Interactive Feedback
by: Pan, Jane, et al.
Published: (2025)

Position on LLM-Assisted Peer Review: Addressing Reviewer Gap through Mentoring and Feedback
by: Yun, JungMin, et al.
Published: (2026)

Why Johnny Can't Use Agents: Industry Aspirations vs. User Realities with AI Agents
by: Shome, Pradyumna, et al.
Published: (2025)

EVOLVE: Emotion and Visual Output Learning via LLM Evaluation
by: Sinclair, Jordan, et al.
Published: (2024)

Generating AI Literacy MCQs: A Multi-Agent LLM Approach
by: Wang, Jiayi, et al.
Published: (2024)

Intersubjective Model of AI-mediated Communication: Augmenting Human-Human Text Chat through LLM-based Adaptive Agent Pair
by: Aoyama, Shutaro, et al.
Published: (2025)

TopoClaw: A Human-Centric and Topology-Aware Agent Operating System
by: Huang, Heyuan, et al.
Published: (2026)

Simulating Teams with LLM Agents: Interactive 2D Environments for Studying Human-AI Dynamics
by: Almutairi, Mohammed, et al.
Published: (2025)

The Effects of Structured LLM-Generated Feedback on Programming Assignment Performance
by: Mihaylova, Tsvetomila, et al.
Published: (2026)