collaborators

7 papers

cs.AI2026

Beyond Pass@k: Measuring Reliability and Security of Agentic Code Generation

Jiajun Jiang, Sharon Zheng, Natan Vidra +1

AI coding agent benchmarks rank agents with the Chen et al. (2021) pass@k estimator, but current implementations misapply it: they set n to the number of unit tests in a single sub…

cs.SE2026

DevIntent: How Much Does LLM-Generated Code Violate Developer Intent?

Susana Haing, Natan Vidra, Spurthi Setty

Code generated by LLMs can violate a developer's implicit intentions when given an ambiguous prompt, yet standard benchmarks measure only whether code passes its stated test. We in…

cs.AI2026

OrchestraBench: Evaluating Multi-Agent Orchestration Failure Modes, Recovery, and Decomposition Quality

Yidian Chen, Yingzi Gu, Natan Vidra +2

Multi-agent orchestration frameworks are moving from demos to production, yet benchmarks typically report task accuracy without diagnosing why a pipeline failed, where a cascade be…

cs.AI2026

Posture and Sustainment Optimization Under Adversarial Uncertainty

Amelie Norris, Alyssa Lee, Natan Vidra +1

Pre-commitment posture, the assignment of military assets to theater locations before conflict scenarios resolve, is a critical and formally unsolved problem in joint operational p…

cs.LG2026

AdvPlan-Bench: Adversarial Evaluation of Structured Plan-Generation Agents

Alina Kapanova, Arun Kanhai, Natan Vidra +1

Structured plan-generation agents are often evaluated as if a plan has quality in isolation, yet many realistic planning tasks require asking how a candidate behaves when another a…

cs.LG2026

MetaRoute-Bench: Evaluating Meta-Decision Policies for Agentic Workflow Routing

Natan Vidra, Alina Kapanova, Arun Kanhai +1

Agentic systems must repeatedly decide whether to answer directly, decompose a task, invoke a tool, execute code, delegate to a specialist, verify an intermediate result, or recove…