The scalability of instructable agents in robotics or gaming is often hindered by limited data that pairs instructions with agent trajectories. However, large datasets of unannotated trajectories containing sequences of various agent behaviour (play trajectories) are often available. In a semi-supervised setup, we explore methods to extract labelled segments from play trajectories. The goal is to augment a small annotated dataset of instruction-trajectory pairs to improve the performance of an instruction-following policy trained downstream via imitation learning. Assuming little variation in segment length, recent video segmentation methods can effectively extract labelled segments. To address the constraint of segment length, we propose Play Segmentation (PS), a probabilistic model that finds maximum likely segmentations of extended subsegments, while only being trained on individual instruction segments. Our results in a game environment and a simulated robotic gripper setting underscore the importance of segmentation; randomly sampled segments diminish performance, while incorporating labelled segments from PS improves policy performance to the level of a policy trained on twice the amount of labelled data.

Do LLMs offer insights into human language learning? A common argument against this idea is that because their architecture and training paradigm are so vastly different from humans, LLMs can learn arbitrary inputs as easily as natural languages. In this paper, we test this claim by training LMs to model impossible and typologically unattested languages. Unlike previous work, which has focused exclusively on English, we conduct experiments on 12 natural languages from 4 language families. Our results show that while GPT-2 small can primarily distinguish attested languages from their impossible counterparts, it does not achieve perfect separation between all the attested languages and all the impossible ones. We further test whether GPT-2 small distinguishes typologically attested from unattested languages with different NP orders by manipulating word order based on Greenberg's Universal 20. We find that the model's perplexity scores do not distinguish attested vs. unattested word orders, as long as the unattested variants maintain constituency structure. These findings suggest that language models exhibit some human-like inductive biases, though these biases are weaker than those found in human learners.

Continual Learning (CL) addresses the problem of learning from a data sequence where the distribution changes over time. Recently, efficient solutions leveraging Pre-Trained Models (PTM) have been widely explored in the offline CL (offCL) scenario, where the data corresponding to each incremental task is known beforehand and can be seen multiple times. However, such solutions often rely on 1) prior knowledge regarding task changes and 2) hyper-parameter search, particularly regarding the learning rate. Both assumptions remain unavailable in online CL (onCL) scenarios, where incoming data distribution is unknown and the model can observe each datum only once. Therefore, existing offCL strategies fall largely behind performance-wise in onCL, with some proving difficult or impossible to adapt to the online scenario. In this paper, we tackle both problems by leveraging Online Prototypes (OP) and Class-Wise Hypergradients (CWH). OP leverages stable output representations of PTM by updating its value on the fly to act as replay samples without requiring task boundaries or storing past data. CWH learns class-dependent gradient coefficients during training to improve over sub-optimal learning rates. We show through experiments that both introduced strategies allow for a consistent gain in accuracy when integrated with existing approaches. We will make the code fully available upon acceptance.

Rapidly Built Medical Crash Cart! Lessons Learned and Impacts on High-Stakes Team Collaboration in the Emergency Room Abstract --Designing robots to support high-stakes teamwork in emergency settings presents unique challenges, including seamless integration into fast-paced environments, facilitating effective communication among team members, and adapting to rapidly changing situations. While teleoperated robots have been successfully used in high-stakes domains such as firefighting and space exploration, autonomous robots that aid high-stakes teamwork remain underexplored. T o address this gap, we conducted a rapid prototyping process to develop a series of seemingly autonomous robot designed to assist clinical teams in the Emergency Room. We transformed a standard crash cart--which stores medical equipment and emergency supplies into a medical robotic crash cart (MCCR). The MCCR was evaluated through field deployments to assess its impact on team workload and usability, identified taxonomies of failure, and refined the MCCR in collaboration with healthcare professionals. By publicly disseminating our MCCR tutorial, we hope to encourage HRI researchers to explore the design of robots for high-stakes teamwork. Teleoperated robots have become indispensable tools for action teams--highly skilled specialist teams that collaborate in short, high-pressure events, requiring improvisation in unpredictable situations [1]. For example, disaster response teams rely on teleoperated robots and drones to aid search and rescue operations [2], [3]. High-stakes military and SW A T teams use teleoperated ordnance disposal [4] and surveillance robots [5] to keep the teams safe. Surgical teams employ teleoperated robots to perform keyhole surgeries with a level of precision that would be unimaginable without these machines [6], [7]. We built three teleoperated medical crash cart robots (MCCRs). MCCR 1 delivers supplies using a hoverboard circuit. MCCR 2 delivers supplies, recommends supplies using drawer opening capabilities, and was deployed at a medical training event which revealed insights.

AI systems are often introduced with high expectations, yet many fail to deliver, resulting in unintended harm and missed opportunities for benefit. We frequently observe significant "AI Mismatches", where the system's actual performance falls short of what is needed to ensure safety and co-create value. These mismatches are particularly difficult to address once development is underway, highlighting the need for early-stage intervention. Navigating complex, multi-dimensional risk factors that contribute to AI Mismatches is a persistent challenge. To address it, we propose an AI Mismatch approach to anticipate and mitigate risks early on, focusing on the gap between realistic model performance and required task performance. Through an analysis of 774 AI cases, we extracted a set of critical factors, which informed the development of seven matrices that map the relationships between these factors and highlight high-risk areas. Through case studies, we demonstrate how our approach can help reduce risks in AI development.

Understanding collaborative writing dynamics between native speakers (NS) and non-native speakers (NNS) is critical for enhancing collaboration quality and team inclusivity. In this paper, we partnered with communication researchers to develop visual analytics solutions for comparing NS and NNS behaviors in 162 writing sessions across 27 teams. The primary challenges in analyzing writing behaviors are data complexity and the uncertainties introduced by automated methods. In response, we present \textsc{COALA}, a novel visual analytics tool that improves model interpretability by displaying uncertainties in author clusters, generating behavior summaries using large language models, and visualizing writing-related actions at multiple granularities. We validated the effectiveness of \textsc{COALA} through user studies with domain experts (N=2+2) and researchers with relevant experience (N=8). We present the insights discovered by participants using \textsc{COALA}, suggest features for future AI-assisted collaborative writing tools, and discuss the broader implications for analyzing collaborative processes beyond writing.

Learning therapeutic counseling involves significant role-play experience with mock patients, with current manual training methods providing only intermittent granular feedback. We seek to accelerate and optimize counselor training by providing frequent, detailed feedback to trainees as they interact with a simulated patient. Our first application domain involves training motivational interviewing skills for counselors. Motivational interviewing is a collaborative counseling style in which patients are guided to talk about changing their behavior, with empathetic counseling an essential ingredient. We developed and evaluated an LLM-powered training system that features a simulated patient and visualizations of turn-by-turn performance feedback tailored to the needs of counselors learning motivational interviewing. We conducted an evaluation study with professional and student counselors, demonstrating high usability and satisfaction with the system. We present design implications for the development of automated systems that train users in counseling skills and their generalizability to other types of social skills training.

Large language models (LLMs) encode a diverse range of linguistic features within their latent representations, which can be harnessed to steer their output toward specific target characteristics. In this paper, we modify the internal structure of LLMs by training sparse autoencoders to learn a sparse representation of the query embedding, allowing precise control over the model's attention distribution. We demonstrate that manipulating this sparse representation effectively transforms the output toward different stylistic and cognitive targets. Specifically, in an educational setting, we show that the cognitive complexity of LLM-generated feedback can be systematically adjusted by modifying the encoded query representation at a specific layer. To achieve this, we guide the learned sparse embedding toward the representation of samples from the desired cognitive complexity level, using gradient-based optimization in the latent space.

Knowledge components (KCs) mapped to problems help model student learning, tracking their mastery levels on fine-grained skills thereby facilitating personalized learning and feedback in online learning platforms. However, crafting and tagging KCs to problems, traditionally performed by human domain experts, is highly labor-intensive. We present a fully automated, LLM-based pipeline for KC generation and tagging for open-ended programming problems. We also develop an LLM-based knowledge tracing (KT) framework to leverage these LLM-generated KCs, which we refer to as KCGen-KT. We conduct extensive quantitative and qualitative evaluations validating the effectiveness of KCGen-KT. On a real-world dataset of student code submissions to open-ended programming problems, KCGen-KT outperforms existing KT methods. We investigate the learning curves of generated KCs and show that LLM-generated KCs have a comparable level-of-fit to human-written KCs under the performance factor analysis (PFA) model. We also conduct a human evaluation to show that the KC tagging accuracy of our pipeline is reasonably accurate when compared to that by human domain experts.

Leveraging multiple large language models (LLMs) to build collaborative multi-agentic workflows has demonstrated significant potential. However, most previous studies focus on prompting the out-of-the-box LLMs, relying on their innate capability for collaboration, which may not improve LLMs' performance as shown recently. In this paper, we introduce a new post-training paradigm MAPoRL (Multi-Agent Post-co-training for collaborative LLMs with Reinforcement Learning), to explicitly elicit the collaborative behaviors and further unleash the power of multi-agentic LLM frameworks. In MAPoRL, multiple LLMs first generate their own responses independently and engage in a multi-turn discussion to collaboratively improve the final answer. In the end, a MAPoRL verifier evaluates both the answer and the discussion, by assigning a score that verifies the correctness of the answer, while adding incentives to encourage corrective and persuasive discussions. The score serves as the co-training reward, and is then maximized through multi-agent RL. Unlike existing LLM post-training paradigms, MAPoRL advocates the co-training of multiple LLMs together using RL for better generalization. Accompanied by analytical insights, our experiments demonstrate that training individual LLMs alone is insufficient to induce effective collaboration. In contrast, multi-agent co-training can boost the collaboration performance across benchmarks, with generalization to unseen domains.