K. J. Kevin Feng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
K. J. Kevin Feng has a total of 50 co-authors. Here are the top co-authors by number of shared publications:
- Amy Xian Zhang
CSE, University of Washington, Seattle, Washington, USA
9 shared publications - David W. McDonald
Human Centered Design & Engineering, University of Washington, Seattle, WA, USA
4 shared publications - Inyoung Cheong
Princeton University, Princeton, NJ, USA, and University of Washington, Seattle, NJ, USA
2 shared publications - Jonathan Bragg
Allen Institute for AI, Seattle, WA, USA
2 shared publications - Joseph Chee Chang
Allen Institute for AI, Seattle, Washington, USA
2 shared publications - Katharina Reinecke
Paul G. Allen School of Computer Science and Engineering, University of Washington, Seattle, Washington, USA
2 shared publications
Latest Publications
- Top Cited PapersOpen Access
- 25 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 1536-1576
The 2025 AI Agent Index: Documenting Technical and Safety Features of Deployed Agentic AI Systems
- 25 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 1536-1576
Top Cited PapersOpen AccessThe 2025 AI Agent Index: Documenting Technical and Safety Features of Deployed Agentic AI Systems
- Open Access
- 26 May 2026
- Published by Association for Computing Machinery (ACM)
- p. 1293-1299
Hedwig: Dynamic Autonomy for Coding Agents Under Local Oversight
Despite coding agents’ advances in handling increasingly complex tasks, their continued tendency to introduce unintended edits, subtle bugs, and scope drift that slip past code review means developers must still decide how much autonomy to grant them. However, existing approaches for setting an agent’s level of autonomy, such as static permission settings or instruction files, cannot account for how developers’ preferences for agent autonomy can shift across tasks and over time. We conducted a formative survey with 21 software engineers who use coding agents and found that they experience frustration with calibrating autonomy and have evolving preferences for level of oversight. Building on these insights, we present Hedwig, a CLI coding agent that dynamically adjusts its autonomy level based on developer-agent interactions across sessions. Rather than operating on a global, fixed autonomy configuration, Hedwig learns an evolving set of behavioral guidelines from developer decisions and feedback, reducing friction on work for which the agent has earned trust, while tightening oversight when the agent operates outside familiar territory. Hedwig demonstrates the potential of a new paradigm where agents intelligently adapt their level of autonomy based on user trust through active, longitudinal collaboration.
- 26 May 2026
- Published by Association for Computing Machinery (ACM)
- p. 1293-1299
Open AccessHedwig: Dynamic Autonomy for Coding Agents Under Local Oversight
Despite coding agents’ advances in handling increasingly complex tasks, their continued tendency to introduce unintended edits, subtle bugs, and scope drift that slip past code review means developers must still decide how much autonomy to grant them. However, existing approaches for setting an agent’s level of autonomy, such as static permission settings or instruction files, cannot account for how developers’ preferences for agent autonomy can shift across tasks and over time. We conducted a formative survey with 21 software engineers who use coding agents and found that they experience frustration with calibrating autonomy and have evolving preferences for level of oversight. Building on these insights, we present Hedwig, a CLI coding agent that dynamically adjusts its autonomy level based on developer-agent interactions across sessions. Rather than operating on a global, fixed autonomy configuration, Hedwig learns an evolving set of behavioral guidelines from developer decisions and feedback, reducing friction on work for which the agent has earned trust, while tightening oversight when the agent operates outside familiar territory. Hedwig demonstrates the potential of a new paradigm where agents intelligently adapt their level of autonomy based on user trust through active, longitudinal collaboration.
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-25
PolicyPad: Collaborative Prototyping of LLM Policies
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-25
Open AccessPolicyPad: Collaborative Prototyping of LLM Policies
- Top Cited PapersOpen Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-23
Cocoa: Co-Planning and Co-Execution with AI Agents
As AI agents take on increasingly long-running tasks involving sophisticated planning and execution, there is a corresponding need for novel interaction designs that enable deeper human-agent collaboration. However, most prior works leverage human interaction to fix “autonomous” workflows that have yet to become fully autonomous or rigidly treat planning and execution as separate stages. Based on a formative study with 9 researchers using AI to support their work, we propose a design that affords greater flexibility in collaboration, so that users can 1) delegate agency to the user or agent via a collaborative plan where individual steps can be assigned; and 2) interleave planning and execution so that plans can adjust after partial execution. We introduce Cocoa, a system that takes design inspiration from computational notebooks to support complex research tasks. A lab study (n = 16) found that Cocoa enabled steerability without sacrificing ease-of-use, and a week-long field deployment (n = 7) showed how researchers collaborated with Cocoa to accomplish real-world tasks.
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-23
Top Cited PapersOpen AccessCocoa: Co-Planning and Co-Execution with AI Agents
As AI agents take on increasingly long-running tasks involving sophisticated planning and execution, there is a corresponding need for novel interaction designs that enable deeper human-agent collaboration. However, most prior works leverage human interaction to fix “autonomous” workflows that have yet to become fully autonomous or rigidly treat planning and execution as separate stages. Based on a formative study with 9 researchers using AI to support their work, we propose a design that affords greater flexibility in collaboration, so that users can 1) delegate agency to the user or agent via a collaborative plan where individual steps can be assigned; and 2) interleave planning and execution so that plans can adjust after partial execution. We introduce Cocoa, a system that takes design inspiration from computational notebooks to support complex research tasks. A lab study (n = 16) found that Cocoa enabled steerability without sacrificing ease-of-use, and a week-long field deployment (n = 7) showed how researchers collaborated with Cocoa to accomplish real-world tasks.
- Open Access
- 22 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 852-867
Interactive Reasoning: Visualizing and Controlling Chain-of-Thought Reasoning in Large Language Models
- 22 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 852-867
Open AccessInteractive Reasoning: Visualizing and Controlling Chain-of-Thought Reasoning in Large Language Models
- Open Access
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-22
Canvil: Designerly Adaptation for LLM-Powered User Experiences
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-22
Open AccessCanvil: Designerly Adaptation for LLM-Powered User Experiences
- Top Cited PapersOpen Access
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-31
IdeaSynth: Iterative Research Idea Development Through Evolving and Composing Idea Facets with Literature-Grounded Feedback
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-31
Top Cited PapersOpen AccessIdeaSynth: Iterative Research Idea Development Through Evolving and Composing Idea Facets with Literature-Grounded Feedback
- Open Access
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Sociotechnical AI Governance: Challenges and Opportunities for HCI
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Open AccessSociotechnical AI Governance: Challenges and Opportunities for HCI
- Top Cited PapersOpen Access
- 3 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 2454-2469
(A)I Am Not a Lawyer, But...: Engaging Legal Experts towards Responsible LLM Policies for Legal Advice
Large language models (LLMs) are increasingly capable of providing users with advice in a wide range of professional domains, including legal advice. However, relying on LLMs for legal queries raises concerns due to the significant expertise required and the potential real-world consequences of the advice. To explore when and why LLMs should or should not provide advice to users, we conducted workshops with 20 legal experts using methods inspired by case-based reasoning. The provided realistic queries (“cases”) allowed experts to examine granular, situation-specific concerns and overarching technical and legal constraints, producing a concrete set of contextual considerations for LLM developers. By synthesizing the factors that impacted LLM response appropriateness, we present a 4-dimension framework: (1) User attributes and behaviors, (2) Nature of queries, (3) AI capabilities, and (4) Social impacts. We share experts’ recommendations for LLM response strategies, which center around helping users identify ‘right questions to ask’ and relevant information rather than providing definitive legal judgments. Our findings reveal novel legal considerations, such as unauthorized practice of law, confidentiality, and liability for inaccurate advice, that have been overlooked in the literature. The case-based deliberation method enabled us to elicit fine-grained, practice-informed insights that surpass those from de-contextualized surveys or speculative principles. These findings underscore the applicability of our method for translating domain-specific professional knowledge and practices into policies that can guide LLM behavior in a more responsible direction.
- 3 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 2454-2469
Top Cited PapersOpen Access(A)I Am Not a Lawyer, But...: Engaging Legal Experts towards Responsible LLM Policies for Legal Advice
Large language models (LLMs) are increasingly capable of providing users with advice in a wide range of professional domains, including legal advice. However, relying on LLMs for legal queries raises concerns due to the significant expertise required and the potential real-world consequences of the advice. To explore when and why LLMs should or should not provide advice to users, we conducted workshops with 20 legal experts using methods inspired by case-based reasoning. The provided realistic queries (“cases”) allowed experts to examine granular, situation-specific concerns and overarching technical and legal constraints, producing a concrete set of contextual considerations for LLM developers. By synthesizing the factors that impacted LLM response appropriateness, we present a 4-dimension framework: (1) User attributes and behaviors, (2) Nature of queries, (3) AI capabilities, and (4) Social impacts. We share experts’ recommendations for LLM response strategies, which center around helping users identify ‘right questions to ask’ and relevant information rather than providing definitive legal judgments. Our findings reveal novel legal considerations, such as unauthorized practice of law, confidentiality, and liability for inaccurate advice, that have been overlooked in the literature. The case-based deliberation method enabled us to elicit fine-grained, practice-informed insights that surpass those from de-contextualized surveys or speculative principles. These findings underscore the applicability of our method for translating domain-specific professional knowledge and practices into policies that can guide LLM behavior in a more responsible direction.
- Open Access
- 11 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-20
Mapping the Design Space of Teachable Social Media Feed Experiences
- 11 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-20
Open AccessMapping the Design Space of Teachable Social Media Feed Experiences