We evaluate through thousands of human-agent interactions, demonstrating 15.4% absolute improvement in instruction execution accuracy

Implicit feedback is widely used in collaborative filtering methods for recommendation.

However, can one do better?

Once language models (LMs) are deployed, they can interact with users long-term, ideally evolving based on their feedback. Asking for direct user feedback can be disruptive; thus, we study harvesting implicit user feedback from user-LM interaction logs. We study two user-LM interaction datasets (WildChat and LMSYS). First, we analyze user feedback in the user-LLM conversation logs, providing insights into when and why such feedback occurs. Second, we study harvesting learning signals from such implicit user feedback. Specifically, we study whether incorporating the contents of user feedback (e.g., user wanted clarification), in addition to the polarity of the feedback, can improve the model performance. We observe mixed results, showing this helps in short human-designed questions (MTBench) but not on longer and more complex questions (WildBench). Together, we provide an in-depth study of implicit user feedback, showing its potential and limitations.

Why Are Car Software Updates Still So Bad? Over-the-air upgrades can not only transform your ride, they can help carmakers slash costs. Despite years of effort and the outlay of billions of dollars, none of the world's automakers have yet to match Tesla's prowess in delivering over-the-air (OTA) software updates. Just like with your phone and laptop, these operating system refreshes allow owners to upgrade their cars remotely. Tesla introduced OTAs in 2012, but now Elon Musk's company pumps out these updates like no other automaker. "Tesla once issued 42 updates within six months," Jean-Marie Lapeyre, Capgemini's CTO for automotive, tells WIRED. But for many other automakers, says Lapeyre, OTAs ship "maybe once a year."

The annual award ceremony features miniature operas, scientific demos, and 24/7 lectures. All products featured on WIRED are independently selected by our editors. However, we may receive compensation from retailers and/or from purchases of products through these links. Does alcohol enhance one's foreign language fluency? Do West African lizards have a preferred pizza topping? And can painting cows with zebra stripes help repel biting flies? These and other unusual research questions were honored tonight in a virtual ceremony to announce the 2025 recipients of the annual Ig Nobel Prizes.

However, can one do better?

The advancement of intelligent agents has revolutionized problem-solving across diverse domains, yet solutions for personalized fashion styling remain underexplored, which holds immense promise for promoting shopping experiences. In this work, we present StyleTailor, the first collaborative agent framework that seamlessly unifies personalized apparel design, shopping recommendation, virtual try-on, and systematic evaluation into a cohesive workflow. To this end, StyleTailor pioneers an iterative visual refinement paradigm driven by multi-level negative feedback, enabling adaptive and precise user alignment. Specifically, our framework features two core agents, i.e., Designer for personalized garment selection and Consultant for virtual try-on, whose outputs are progressively refined via hierarchical vision-language model feedback spanning individual items, complete outfits, and try-on efficacy. Counterexamples are aggregated into negative prompts, forming a closed-loop mechanism that enhances recommendation quality. To assess the performance, we introduce a comprehensive evaluation suite encompassing style consistency, visual quality, face similarity, and artistic appraisal. Extensive experiments demonstrate StyleTailor's superior performance in delivering personalized designs and recommendations, outperforming strong baselines without negative feedback and establishing a new benchmark for intelligent fashion systems.

In this interview series, we're meeting some of the AAAI/SIGAI Doctoral Consortium participants to find out more about their research. Kate Candon is a PhD student at Yale University interested in understanding how we can create interactive agents that are more effectively able to help people. We spoke to Kate to find out more about how she is leveraging explicit and implicit feedback in human-robot interactions. Specifically I'm interested in how we can get robots to better learn from humans in the way that they naturally teach. Typically, a lot of work in robot learning is with a human teacher who is only tasked with giving explicit feedback to the robot, but they're not necessarily engaged in the task.