Customer-obsessed science

Training large foundation models for agentic tasks is increasingly impractical due to the high computational costs, long iteration cycles, and rapid obsolescence as new models are continuously released. Instead of post-training massive models for every new task or domain, we propose Supplement Generation Training (SGT), a more efficient and sustainable strategy. SGT trains a smaller LLM to generate useful

Tool-calling agents are increasingly deployed in real-world customer-facing workflows. Yet most studies on tool-calling agents focus on idealized settings with general, fixed, and well-specified tasks. In real-world applications, user requests are often (1) ambiguous, (2) changing over time, or (3) infeasible due to policy constraints, and training and evaluation data that cover these diverse, complex interaction

Conventional adaptive bitrate (ABR) streaming systems typically rely on static bitrate ladders to optimize Quality of Experience (QoE). While operationally simple, this 'one-size-fits-all' approach neglects content-specific characteristics, often compromising streaming efficiency. Per-title optimization methods address this by predicting the rate-distortion convex hull directly from the source content,

LLMs can perform multi-step reasoning through Chain-of-Thought (CoT), but they cannot reliably verify their own logic. Even when they reach correct answers, the underlying reasoning may be flawed, undermining trust in high-stakes scenarios. To mitigate this issue, we introduce VERICOT, a neuro-symbolic method that extracts and verifies formal logical arguments from CoT reasoning. VERICOT formalizes each

Search-augmented LLM agents can produce deep research reports (DRRs), but claim-level factuality remains hard to verify. Existing fact-checkers are optimized for short, general-domain claims and often reduce verification to matching snippets or checking cited sources, missing uncited synthesis and broader scientific consensus. Yet evaluating better DRR verifiers is itself difficult: the usual solution,