4 papers
Before They Can Solve: Predicting Post-Training Coding-Agent Performance from Base Models
Tan Yu, Alexander Bukharin, Khushi Bhardwaj +19
How can we predict which base checkpoint is worth an expensive round of agentic post-training? End-to-end pass@ tests whether successful behavior already appears in a base model…
Risk-Aware Adaptive Evaluation: Finding High-Impact Failures Under Limited Budgets
Priyanath Maji, Spandan Ghose Chowdhury
Evaluating interactive agents is expensive. Agent behavior is stochastic, so reliability must be measured over repeated trials, but failures are rare and differ widely in how much…
Commitment Hierarchies under Intent Revision: A Belief-Revision Account of Salvage in Tool-Use Agents
Spandan Ghose Chowdhury
When a user changes their mind partway through a task, an agent that has already split the task into sub-goals and paid for tool calls must decide, per cached sub-result, whether t…
Selection Bias Correction in Retail Intelligence
Spandan Ghose Chowdhury
Retail intelligence often relies on monitoring popular, high-velocity products, potentially biasing economic indicators by ignoring the "long tail" of niche items. This simulation…