We have 9 of 134 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 paper recast context compression as a causal decision preservation problem over discrete interaction units and introduces FOCUS, a training-free context compression framework that operates entirely at test time that requires no offline data collection or fine-tuning.
Pseudo Self-Distillation is presented, a framework that enables small language models to construct hierarchical memory representations by distilling behavior from a strong black-box oracle through a multi-stage training pipeline, with off-policy PSD achieving the strongest results across most conditions.
We study length inflation in on-policy distillation (OPD), where student responses can become excessively long and even exhaust the generation budget. We identify \emph{termination-token mismatch} between base students and post-trained teachers as an important source of this behavior. Across Qwen3, Llama, and Gemma, th...
To mitigate the human cost of failure attribution, AgentRx is presented, an automated diagnostic framework that pinpoints the critical failure step in a failed agent trajectory and improves step localization by 75% on average over prior work, while providing failure category attribution.
TSGen, an automated pipeline for generating high-quality, structured TSGs from historical incident reports using large language models (LLMs), consists of filtering and classifying incident data into diagnostically relevant categories and distilling core incidents to ensure diversity and generalizability.
This work introduces WebXSkill, a framework that bridges a grounding gap with executable skills, each pairing a parameterized action program with step-level natural-language guidance, and finds that better skill deployment mode depends on a model's plan and execution capability.
DepRepair is proposed, a single-call LLM approach that grounds repair in structured upstream evidence through three components: an evidence filter that distills relevant upstream changes, a usage locator that identifies affected consumer sites, and a subcategory-aware guide that tailors repairs to the breaking-change t...
This work proposes and develops an open-source policy simulation framework, LoadStar, which forms a reusable benchmark pipeline for validating policies for resource-centric NoSQL workloads, and defines a resource optimization problem for placing Cosmos DB replicas onto VM nodes, and develops the Luna model for forecast...
Large language model (LLM) agents are increasingly used for multi-step, stateful tool-use tasks, yet production reliability remains limited. Unlike static software repair, agent repair must recover dynamic trajectories whose early decisions can propagate into later errors and external state changes. Existing automatic...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
