arXiv subjects

Chi Cheng

Publications and source records attributed to Chi Cheng.

3 recordsLinked to original sources

arXiv2026

Evaluating Enterprise Analytics Agents: An End-to-End, Trace-Backed Methodology

Enterprise analytics agents are not only text-to-SQL systems. They interpret business intent and choose metric definitions. They select data sources, execute tools, inspect results, and produce natural-language answers. Those answers may influence operational, financial, or executive decisions. Grading final answers hides where these agents fail. A plausible answer can use the wrong source of truth. It can skip a required decomposition, claim causality without support, or change its table interpretation across repeated runs. We present an end-to-end evaluation methodology for analytics agents. The methodology grades agent behavior across three families: semantic understanding, execution quality, and reliability. Grading uses question banks with human-written golden answers, repeated runs, and runtime traces. Each run first passes a run-validity check, then receives tiered, abstention-aware scores that feed a decision framework rather than a release gate. We instantiate the methodology on a controlled internal analytics agent at a large online marketplace. The case study uses 50 analytics questions, two anonymous model configurations, and three randomized repetitions per configuration, yielding 300 traces. The higher-capability configuration reduced early refusal from 73% to 0% and increased real-data answers from 21% to 73%. However, it also exhausted the tool-round budget on 16% of runs. It overran the schema-exploration budget on 77% of traces. It changed its table interpretation on 41 of 50 questions. On finance questions with structured golden answers, source table use and escalation improved, but canonical decomposition remained weak in both configurations. These results show why trust in analytics agents requires end-to-end, trace-backed evaluation rather than SQL correctness or final answer quality alone.

cs.SE↗

arXiv2025

LinguaFluid: Language Guided Fluid Control via Semantic Rewards in Reinforcement Learning

In the domain of scientific machine learning, designing effective reward functions remains a challenge in reinforcement learning (RL), particularly in environments where task goals are difficult to specify numerically. Reward functions in existing work are predominantly based on heuristics, manual engineering, or task-specific tuning. In this work, we introduce a semantically aligned reinforcement learning method where rewards are computed by aligning the current state with a target semantic instruction using a Sentence-Bidirectional Encoder Representations from Transformers (SBERT). Instead of relying on manually defined reward functions, the policy receives feedback based on the reward, which is a cosine similarity between the goal textual description and the statement description in the episode. We evaluated our approach in several environments and showed that semantic reward can guide learning to achieve competitive control behavior, even in the absence of hand-crafted reward functions. Our study demonstrates a correlation between the language embedding space and the conventional Euclidean space. This framework opens new horizons for aligning agent behavior with natural language goals and lays the groundwork for a more seamless integration of larger language models (LLMs) and fluid control applications.

cs.LG↗

arXiv2018

Lighting the Way to a Smart World: Lattice-Based Cryptography for Internet of Things

The Ukraine power grid cyberattacks remind us that the smart Internet of Things (IoT) can help us control our light-bulbs, but if under attacks it might also take us into darkness. Nowadays, many literatures have tried to address the concerns on IoT security, but few of them take into consideration the sever threats to IoT coming from the advances of quantum computing. As a promising candidate for the future post-quantum cryptography standard, lattice-based cryptography enjoys the advantages of strong security guarantees and high efficiency, which make it extremely suitable for IoT applications. In this paper, we summarize the advantages of lattice-based cryptography and the state of art of their implementations for IoT devices.

cs.CR↗