Raj Korpan

Organizers Of QueerInAI, Anaelia Ovalle, Arjun Subramonian et al. · allen-ai, cmu

We present Queer in AI as a case study for community-led participatory design in AI. We examine how participatory design and intersectional tenets started and shaped this community's programs over the years. We discuss different challenges that emerged in the process, look at ways this organization has fallen short of operationalizing participatory and intersectional principles, and then assess the organization's impact. Queer in AI provides important lessons and insights for practitioners and theorists of participatory methods broadly through its rejection of hierarchy in favor of decentralization, success at building aid and programs by and for the queer community, and effort to change actors and institutions outside of the queer community. Finally, we theorize how communities like Queer in AI contribute to the participatory design in AI more broadly by fostering cultures of participation in AI, welcoming and empowering marginalized participants, critiquing poor or exploitative participatory practices, and bringing participation to institutions outside of individual research projects. Queer in AI's work serves as a case study of grassroots activism and participatory methods within AI, demonstrating the potential of community-led participatory methods and intersectional praxis, while also providing challenges, case studies, and nuanced insights to researchers developing and using participatory methods.

Luke Nicholls, Robert Hutto, Zephrah Soto et al.

Extended interaction with large language models (LLMs) has been linked to the reinforcement of delusional beliefs, a phenomenon attracting growing clinical and public concern. Yet most empirical work evaluates model safety in brief interactions, which may not reflect how these harms develop through sustained dialogue. We tested five models across three levels of accumulated context, using the same escalating delusional history to isolate its effect on model behaviour. Human raters coded responses on risk and safety dimensions, and each model was analysed qualitatively. Models separated into two distinct tiers: GPT-4o, Grok 4.1 Fast, and Gemini 3 Pro exhibited high-risk, low-safety profiles; Claude Opus 4.5 and GPT-5.2 Instant displayed the opposite pattern. As context accumulated, performance tended to degrade in the unsafe group, while the same material activated stronger safety interventions among the safer models. Qualitative analysis identified distinct mechanisms of failure, including validation of the user's delusional premises, elaboration beyond them, and attempting harm reduction from within the delusional frame. Safer models, however, often used the established relationship to support intervention, taking accountability for past missteps so that redirection would not be received as betrayal. These findings indicate that accumulated context functions as a stress test of safety architecture, revealing whether a model treats prior dialogue as a worldview to inherit or as evidence to evaluate. Short-context assessments may therefore mischaracterise model safety, underestimating danger in some systems while missing context-activated gains in others. The results suggest that delusional reinforcement by LLMs reflects a preventable alignment failure. In demonstrating that these harms can be resisted, the safer models establish a baseline future systems should now be expected to meet.

Raj Korpan

This paper presents VBMO, the Voting-Based Multi-Objective path planning algorithm, that generates optimal single-objective plans, evaluates each of them with respect to the other objectives, and selects one with a voting mechanism. VBMO does not use hand-tuned weights, consider the multiple objectives at every step of search, or use an evolutionary algorithm. Instead, it considers how a plan that is optimal in one objective may perform well with respect to others. VBMO incorporates three voting mechanisms: range, Borda, and combined approval. Extensive evaluation in diverse and complex environments demonstrates the algorithm's ability to efficiently produce plans that satisfy multiple objectives.

Daniel Weiner, Raj Korpan

In role-playing games (RPGs), the level of immersion is critical-especially when an in-game agent conveys tasks, hints, or ideas to the player. For an agent to accurately interpret the player's emotional state and contextual nuances, a foundational level of understanding is required, which can be achieved using a Large Language Model (LLM). Maintaining the LLM's focus across multiple context changes, however, necessitates a more robust approach, such as integrating the LLM with a dedicated task allocation model to guide its performance throughout gameplay. In response to this need, we introduce Voting-Based Task Assignment (VBTA), a framework inspired by human reasoning in task allocation and completion. VBTA assigns capability profiles to agents and task descriptions to tasks, then generates a suitability matrix that quantifies the alignment between an agent's abilities and a task's requirements. Leveraging six distinct voting methods, a pre-trained LLM, and integrating conflict-based search (CBS) for path planning, VBTA efficiently identifies and assigns the most suitable agent to each task. While existing approaches focus on generating individual aspects of gameplay, such as single quests, or combat encounters, our method shows promise when generating both unique combat encounters and narratives because of its generalizable nature.

Raj Korpan

As robots take on caregiving roles, ensuring equitable and unbiased interactions with diverse populations is critical. Although Large Language Models (LLMs) serve as key components in shaping robotic behavior, speech, and decision-making, these models may encode and propagate societal biases, leading to disparities in care based on demographic factors. This paper examines how LLM-generated responses shape robot caregiving characteristics and responsibilities when prompted with different demographic information related to sex, gender, sexuality, race, ethnicity, nationality, disability, and age. Findings show simplified descriptions for disability and age, lower sentiment for disability and LGBTQ+ identities, and distinct clustering patterns reinforcing stereotypes in caregiving narratives. These results emphasize the need for ethical and inclusive HRI design.

Casey Kennington, Malihe Alikhani, Heather Pon-Barry et al. · cmu

The ability to interact with machines using natural human language is becoming not just commonplace, but expected. The next step is not just text interfaces, but speech interfaces and not just with computers, but with all machines including robots. In this paper, we chronicle the recent history of this growing field of spoken dialogue with robots and offer the community three proposals, the first focused on education, the second on benchmarks, and the third on the modeling of language when it comes to spoken interaction with robots. The three proposals should act as white papers for any researcher to take and build upon.

Raj Korpan, Susan L. Epstein

To perform tasks well in a new domain, one must first know something about it. This paper reports on a robot controller for navigation through unfamiliar indoor worlds. Based on spatial affordances, it integrates planning with reactive heuristics. Before it addresses specific targets, however, the system deliberately explores for high-level connectivity and captures that data in a cognitive spatial model. Despite limited exploration time, planning in the resultant model is faster and better supports successful travel in a challenging, realistic space.

Anoop Aroor, Susan L. Epstein, Raj Korpan

While effective navigation in large, crowded environments is essential for an autonomous robot, preliminary testing of algorithms to support it requires simulation across a broad range of crowd scenarios. Most available simulation tools provide either realistic crowds without robots or realistic robots without realistic crowds. This paper introduces MengeROS, a 2-D simulator that realistically integrates multiple robots and crowds. MengeROS provides a broad range of settings in which to test the capabilities and performance of navigation algorithms designed for large crowded environments.

Raj Korpan, Susan L. Epstein, Anoop Aroor et al.

Effective collaboration between a robot and a person requires natural communication. When a robot travels with a human companion, the robot should be able to explain its navigation behavior in natural language. This paper explains how a cognitively-based, autonomous robot navigation system produces informative, intuitive explanations for its decisions. Language generation here is based upon the robot's commonsense, its qualitative reasoning, and its learned spatial model. This approach produces natural explanations in real time for a robot as it navigates in a large, complex indoor environment.