Abel Lim

Zairah Mustahsan, Abel Lim, Megna Anand et al.

As large language models become components of larger agentic systems, evaluation reliability becomes critical: unreliable sub-agents introduce brittleness into downstream system behavior. Yet current evaluation practice, reporting a single accuracy number from a single run, obscures the variance underlying these results, making it impossible to distinguish genuine capability improvements from lucky sampling. We propose adopting Intraclass Correlation Coefficient (ICC), a metric from measurement science, to characterize this variance. ICC decomposes observed variance into between-query variance (task difficulty) and within-query variance (agent inconsistency), highlighting whether reported results reflect true capability or measurement noise. We evaluated on GAIA (Levels 1-3, measuring agentic capabilities across varying reasoning complexity) and FRAMES (measuring retrieval and factuality across multiple documents). We found that ICC varies dramatically with task structure, with reasoning and retrieval tasks (FRAMES) exhibit ICC=0.4955-0.7118 across models, and agentic tasks (GAIA) exhibiting ICC=0.304-0.774 across models. For sub-agent replacement decisions in agentic systems, accuracy improvements are only trustworthy if ICC also improves. We demonstrate that ICC converges by n=8-16 trials for structured tasks and n>=32 for complex reasoning, enabling practitioners to set evidence-based resampling budgets. We recommend reporting accuracy alongside ICC and within-query variance as standard practice, and propose updated Evaluation Cards capturing these metrics. By making evaluation stability visible, we aim to transform agentic benchmarking from opaque leaderboard competition to trustworthy experimental science. Our code is open-sourced at https://github.com/youdotcom-oss/stochastic-agent-evals.

Julian Nubert, Nicholas Giai Truong, Abel Lim et al.

The goal of this project is to introduce and present a machine learning application that aims to improve the quality of life of people in Singapore. In particular, we investigate the use of machine learning solutions to tackle the problem of traffic congestion in Singapore. In layman's terms, we seek to make Singapore (or any other city) a smoother place. To accomplish this aim, we present an end-to-end system comprising of 1. A traffic density estimation algorithm at traffic lights/junctions and 2. a suitable traffic signal control algorithms that make use of the density information for better traffic control. Traffic density estimation can be obtained from traffic junction images using various machine learning techniques (combined with CV tools). After research into various advanced machine learning methods, we decided on convolutional neural networks (CNNs). We conducted experiments on our algorithms, using the publicly available traffic camera dataset published by the Land Transport Authority (LTA) to demonstrate the feasibility of this approach. With these traffic density estimates, different traffic algorithms can be applied to minimize congestion at traffic junctions in general.