Carlo Bosio

Yiyou Sun, Xinyang Han, Weichen Zhang et al.

Recent AI systems have achieved strong results on a wide range of benchmarks, yet these gains have not translated into economically meaningful deployment across many professional domains. We argue that this gap is largely an evaluation problem: widely used benchmarks lack sustained performance measurement on real and economically valuable workflows. This paper introduces Agents' Last Exam (ALE), a benchmark designed to evaluate AI agents on long-horizon, economically valuable, real-world tasks with verifiable outcomes. Developed in collaboration with 250+ industry experts, ALE covers non-physical industries defined with reference to O*NET / SOC 2018 (the U.S. federal occupational taxonomy). It is organized around a task taxonomy with 55 subfields grouped into 13 industry clusters covering 1K+ tasks. Current results show that the hardest tier remains far from saturated: across mainstream harness and backbone configurations, the average full pass rate is 2.6%. ALE is designed as a living benchmark: its task pool grows continuously as new workflows and industries are onboarded. More broadly, ALE is intended not merely as another leaderboard, but as an instrument for closing the gap between benchmark success and GDP-relevant impact.

Long Phan, Alice Gatti, Ziwen Han et al. · amazon-science, apple-ml

Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achieve over 90\% accuracy on popular benchmarks like MMLU, limiting informed measurement of state-of-the-art LLM capabilities. In response, we introduce Humanity's Last Exam (HLE), a multi-modal benchmark at the frontier of human knowledge, designed to be the final closed-ended academic benchmark of its kind with broad subject coverage. HLE consists of 2,500 questions across dozens of subjects, including mathematics, humanities, and the natural sciences. HLE is developed globally by subject-matter experts and consists of multiple-choice and short-answer questions suitable for automated grading. Each question has a known solution that is unambiguous and easily verifiable, but cannot be quickly answered via internet retrieval. State-of-the-art LLMs demonstrate low accuracy and calibration on HLE, highlighting a significant gap between current LLM capabilities and the expert human frontier on closed-ended academic questions. To inform research and policymaking upon a clear understanding of model capabilities, we publicly release HLE at https://lastexam.ai.

Carlo Bosio, Matteo Guarrera, Alberto Sangiovanni-Vincentelli et al.

Large Language models (LLMs) have shown promise as generators of symbolic control policies, producing interpretable program-like representations through iterative search. However, these models are not capable of separating the functional structure of a policy from the numerical values it is parametrized by, thus making the search process slow and inefficient. We propose a hybrid approach that decouples structural synthesis from parameter optimization by introducing an additional optimization layer for local parameter search. In our method, the numerical parameters of LLM-generated programs are extracted and optimized numerically to maximize task performance. With this integration, an LLM iterates over the functional structure of programs, while a separate optimization loop is used to find a locally optimal set of parameters accompanying candidate programs. We evaluate our method on a set of control tasks, showing that it achieves higher returns and improved sample efficiency compared to purely LLM-guided search. We show that combining symbolic program synthesis with numerical optimization yields interpretable yet high-performing policies, bridging the gap between language-model-guided design and classical control tuning. Our code is available at https://sites.google.com/berkeley.edu/colmo.

Eric Foss, Andrew Tai, Carlo Bosio et al.

Collaborative aerial transportation of tethered payloads is fundamentally limited by space, power, and weight constraints. Conventional approaches rely on static equilibrium conditions, where each vehicle tilts to generate the forces that ensure they maintain a formation geometry that avoids aerodynamic interactions and collision. This horizontal thrust component represents a significant energy penalty compared to the ideal case in which each vehicle produces purely vertical thrust to lift the payload. Operating in tighter tether configurations can minimize this effect, but at the cost of either having to fly the vehicles in closer proximity, which risks collision, or significantly increasing the length of the tether, which increases complexity and reduces potential use-cases. We propose operating the tether-suspended flying system at a rotating equilibrium. By maintaining steady circular motion, centrifugal forces provide the necessary horizontal tether tension, allowing each quadrotor to generate purely vertical thrust and thus reducing the total force (and power) required compared to an equilibrium where the thrusts are not vertical. It also allows for a wider range of tether configurations to be used without sacrificing efficiency. Results demonstrate that rotating equilibria can reduce power consumption relative to static lifting by up to 20%, making collaborative aerial solutions more practically relevant.

Carlo Bosio, Greg Woelki, Noureldin Hendy et al.

Human drivers focus only on a handful of agents at any one time. On the other hand, autonomous driving systems process complex scenes with numerous agents, regardless of whether they are pedestrians on a crosswalk or vehicles parked on the side of the road. While attention mechanisms offer an implicit way to reduce the input to the elements that affect decisions, existing attention mechanisms for capturing agent interactions are quadratic, and generally computationally expensive. We propose RDAR, a strategy to learn per-agent relevance -- how much each agent influences the behavior of the controlled vehicle -- by identifying which agents can be excluded from the input to a pre-trained behavior model. We formulate the masking procedure as a Markov Decision Process where the action consists of a binary mask indicating agent selection. We evaluate RDAR on a large-scale driving dataset, and demonstrate its ability to learn an accurate numerical measure of relevance by achieving comparable driving performance, in terms of overall progress, safety and performance, while processing significantly fewer agents compared to a state of the art behavior model.