We have 10 of 16 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
This work systematically evaluates 16 PI configurations across three multi-turn agentic benchmarks and three student models that vary in scale and reasoning mode and finds that PI effectiveness depends on its content, generation source, and the student model.
In-context learning (ICL) allows language models to adapt their behavior from instructions and demonstrations in a prompt, but accuracy alone does not reveal how contextual information controls their predictions. We study the acquisition and trainability of ICL with a controlled diagnostic that separates copying a near...
Environments are the foundation of recursive self-improvement: they provide the problems agents work on and the feedback used to evaluate progress. Yet constructing challenging research environments with reliable evaluation still depends on domain experts, limiting their scale and disciplinary coverage. We introduce RS...
Humans perceive far more in a scene than what is explicitly depicted: a single glance captures past causes and future trajectories; a quick peek determines if a vehicle can fit between two parked cars; a few seconds of video reveals who holds authority in a room; and a fleeting clip highlights subtle abstract patterns...
The increasing deployment of AI agents in long-horizon tasks yields massive execution logs. Diagnosing failures within these records is crucial for reliability, as it transforms outcome-level signals into actionable interventions. The sheer scale of the data renders human review impractical, driving the need for automa...
SteerDuplex is introduced, a Moshi-based full-duplex speech model fine-tuned on natural conversations and synthetic dialogues targeting instruction following, vocal delivery, reasoning, and duplex interaction, and two-stage reinforcement learning with hybrid rewards to improve timing and response continuity.
Reliable Enterprise Agent Deployment (READY), a framework for qualifying AI agents for deployment on enterprise workflows, and provides a basis for comparing agent systems, setting oversight requirements, and making evidence-based deployment decisions.
CRAFT is introduced, a method that converts any rubric based evaluation dataset into a model specific diagnosis of weak capabilities, and yields both a sharper picture of what a model cannot do and measurably better models after finetuning on that diagnosis.
This work proposes Rubric Dropout, a one-line fix borrowed from neuron dropout that randomly drops a subset of the rubric's criteria before computing the reward, so the policy never optimizes the same rubric twice.
This work introduces an interaction-centric taxonomy that localizes failures to the interactions in which they originate and identifies the responsible component, and organizes 41 failure modes by assigning each to an edge between two components and a fault side indicating where the repair belongs.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
