K. J. Kevin Feng

K. J. Kevin Feng, Quan Ze Chen, Inyoung Cheong et al. · uw

Case studies commonly form the pedagogical backbone in law, ethics, and many other domains that face complex and ambiguous societal questions informed by human values. Similar complexities and ambiguities arise when we consider how AI should be aligned in practice: when faced with vast quantities of diverse (and sometimes conflicting) values from different individuals and communities, with whose values is AI to align, and how should AI do so? We propose a complementary approach to constitutional AI alignment, grounded in ideas from case-based reasoning (CBR), that focuses on the construction of policies through judgments on a set of cases. We present a process to assemble such a case repository by: 1) gathering a set of ``seed'' cases -- questions one may ask an AI system -- in a particular domain, 2) eliciting domain-specific key dimensions for cases through workshops with domain experts, 3) using LLMs to generate variations of cases not seen in the wild, and 4) engaging with the public to judge and improve cases. We then discuss how such a case repository could assist in AI alignment, both through directly acting as precedents to ground acceptable behaviors, and as a medium for individuals and communities to engage in moral reasoning around AI.

K. J. Kevin Feng, Tae Soo Kim, Rock Yuren Pang et al. · allen-ai

AI agents that take actions in their environment autonomously over extended time horizons require robust governance interventions to curb their potentially consequential risks. Prior proposals for governing AI agents primarily target system-level safeguards (e.g., prompt injection monitors) or agent infrastructure (e.g., agent IDs). In this work, we explore a complementary approach: regulating user interfaces of AI agents as a way of enforcing transparency and behavioral requirements that then demand changes at the system and/or infrastructure levels. Specifically, we analyze 22 existing agentic systems to identify UI elements that play key roles in human-agent interaction and communication. We then synthesize those elements into six high-level interaction design patterns that hold regulatory potential (e.g., requiring agent memory to be editable). We conclude with policy recommendations based on our analysis. Our work exposes a new surface for regulatory action that supplements previous proposals for practical AI agent governance.

Tanjal Shukla, K. J. Kevin Feng, Leijie Wang et al.

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.

Inyoung Cheong, King Xia, K. J. Kevin Feng et al. · uw

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 \textit{when} and \textit{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.

K. J. Kevin Feng, David W. McDonald, Amy X. Zhang

Autonomy is a double-edged sword for AI agents, simultaneously unlocking transformative possibilities and serious risks. How can agent developers calibrate the appropriate levels of autonomy at which their agents should operate? We argue that an agent's level of autonomy can be treated as a deliberate design decision, separate from its capability and operational environment. In this work, we define five levels of escalating agent autonomy, characterized by the roles a user can take when interacting with an agent: operator, collaborator, consultant, approver, and observer. Within each level, we describe the ways by which a user can exert control over the agent and open questions for how to design the nature of user-agent interaction. We then highlight a potential application of our framework towards AI autonomy certificates to govern agent behavior in single- and multi-agent systems. We conclude by proposing early ideas for evaluating agents' autonomy. Our work aims to contribute meaningful, practical steps towards responsibly deployed and useful AI agents in the real world.

Rock Yuren Pang, K. J. Kevin Feng, Shangbin Feng et al. · uw

The output quality of large language models (LLMs) can be improved via "reasoning": generating segments of chain-of-thought (CoT) content to further condition the model prior to producing user-facing output. While these chains contain valuable information, they are verbose and lack explicit organization, making them tedious to review. Moreover, they lack opportunities for user feedback, such as to remove unwanted considerations, add desired ones, or clarify unclear assumptions. We introduce Interactive Reasoning, an interaction design that visualizes chain-of-thought outputs as a hierarchy of topics and enables user review and modification. We implement interactive reasoning in Hippo, a prototype for AI-assisted decision making in the face of uncertain trade-offs. In a user study with 16 participants, we find that interactive reasoning in Hippo allows users to quickly identify and interrupt erroneous generations, efficiently steer the model towards customized responses, and better understand both model reasoning and model outputs. Our work contributes to a new paradigm that incorporates user oversight into LLM reasoning processes.

Quan Ze Chen, K. J. Kevin Feng, Chan Young Park et al.

When different groups' values differ, one approach to model alignment is to steer models at inference time towards each group's preferences. However, techniques like in-context learning only consider similarity when drawing few-shot examples and not cross-group differences in values. We propose SPICA, a framework that accounts for group-level differences during in-context example retrieval. SPICA introduces three designs: scenario banks, group-informed retrieval metrics, and in-context alignment prompts. From an evaluation of SPICA on an alignment task collecting inputs from four demographic groups ($n = 544$), our metrics retrieve in-context examples that more closely match observed preferences, with the best prompt configuration using multiple contrastive responses to demonstrate examples. In an end-to-end evaluation ($n = 120$), we observe that SPICA is higher rated than similarity-based retrieval, with groups seeing up to a +0.16 point improvement on a 5 point scale. Additionally, gains from SPICA were more uniform, with all groups benefiting from alignment rather than only some. Finally, we find that while a group-agnostic approach can align to aggregated values, it is not most suited for divergent groups.

K. J. Kevin Feng, Tzu-Sheng Kuo, Quan Ze et al.

As LLMs gain adoption in high-stakes domains like mental health, domain experts are increasingly consulted to provide input into policies governing their behavior. From an observation of 19 policymaking workshops with 9 experts over 15 weeks, we identified opportunities to better support rapid experimentation, feedback, and iteration for collaborative policy design processes. We present PolicyPad, an interactive system that facilitates the emerging practice of LLM policy prototyping by drawing from established UX prototyping practices, including heuristic evaluation and storyboarding. Using PolicyPad, policy designers can collaborate on drafting a policy in real time while independently testing policy-informed model behavior with usage scenarios. We evaluate PolicyPad through workshops with 8 groups of 22 domain experts in mental health and law, finding that PolicyPad enhanced collaborative dynamics during policy design, enabled tight feedback loops, and led to novel policy contributions. Overall, our work paves participatory paths for advancing AI alignment and safety.