A recurrent-depth language model reuses one block of weights several times in a row. The number of repetitions, which we call loops, is chosen when the model runs, not when it is trained, and running fewer is cheaper and faster, so a deployment may choose to do it. Running fewer loops also makes these models less safe,...
Large language models are increasingly used in computer science education. However, the teaching abilities of even the most powerful LLMs are limited: they tend to reveal the solution prematurely and may lose focus on the learner's current debugging objective. To address this, we introduce SocraticRepair, a planning-gu...
Mykhailo Kopytskyi, Jian-Hua Yang, Mir Seyedebrahimi· 0 citations
Batch risk-based inspection scheduling struggles to detect a critical failure class: food facilities with recent clean inspections that subsequently develop severe violations. Traditional systems recompute risk on fixed planning cycles using static historical data, leaving blind spots between inspection cycles. To addr...
We ask whether a tool-using agent whose sole duty is to keep humans alive can be induced, by delayed prompt injection, to kill. The keep-alive duty is in force from the first watch, with the attack arriving later, appended to otherwise truthful telemetry the operator is required to read. Experiments are based on a NASA...
Josef A. Habdank· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Recent work on self-evolving LLM agents treats the agent harness as an optimization target that can be iteratively improved through execution feedback. Existing approaches, however, largely optimize a single objective and evolve the harness as a monolithic artifact, limiting their ability to handle competing goals and...
Wei-Cheng Yu, Lesly Miculicich, Bhavana Dalvi et al.· 0 citations
Single-step retrosynthesis is a one-to-many inverse problem, yet most models are trained and evaluated against a single recorded reactant set. Reference-based training gives no explicit positive signal for unrecorded alternatives, and exact-match evaluation rejects non-matching predictions regardless of chemical plausi...
Trust calibration remains the dominant framing of AI-assisted decision making: the goal is to close the gap between perceived and actual trustworthiness of AI systems so that users rely on them appropriately. We argue that this approach, while useful for decision problems that are well-defined and clearly scoped, overl...
GesBench is introduced: a human-grounded benchmark for cue-level social perception in multimodal LLMs and shifts social evaluation from whether models eventually recognize meaning to when and where that meaning is formed.
Chain-of-thought prompting enables reasoning in large language models but produces explanations that are difficult to verify, expensive to generate, and not always faithful. We introduce a Structural Chain-of-Thought framework where models generate executable computational graphs instead of free-form reasoning. The fin...
Petr Senatorov, Karim Vafin, Elena Tutubalina et al.· 0 citations
Visual agents that interleave reasoning with tool invocation have posed a promising direction for multimodal tasks. However, learning effective tool invocation usually relies on curated question-answer pairs or expert demonstrations at scale, which are expensive to acquire. In this study, we propose Marvo, a simple-yet...
Wen-Xi Yang, Yu-Zhong Zhao, Bao-Chang Zhang et al.· 0 citations
Adapting to a new world and reasoning correctly about which outcomes are possible under rules one has not met before is a basic capacity underlying general intelligence. We study it in small discrete worlds: sets of grid configurations consistent with a shared set of rules, concretely Sudoku-like puzzles built from a c...
Supporting edge Artificial Intelligence (AI) inference as a network service is challenging because current mobile systems can transport tensors but do not expose or understand the inference context that gives those tensors operational meaning. Prior studies have addressed this gap through dynamic partitioning, collabor...
Rodrigo Moreira, Larissa Ferreira Rodrigues Moreira, Joberto S. B. Martins et al.· 0 citations
