Wen Wang

OrchJail introduces an orchestration-guided fuzzing framework to systematically jailbreak tool-calling text-to-image agents by exploiting unsafe multi-step tool-orchestration patterns.

MIRA proposes a novel source-aware filtering framework that discovers and anchors evaluation rubrics during data selection, significantly improving code-oriented mid-training data quality while reducing token usage.

SeClaw is a new framework that synthesizes security tasks from structured risk specifications to evaluate autonomous LLM agents' behavior in stateful environments, focusing on the process of unsafe actions rather than just the final outcome.

SeClaw is a new framework that uses specification-driven task synthesis to create comprehensive and controllable security benchmarks for evaluating the unsafe behaviors of autonomous LLM agents.

The paper introduces StreamMA, a streaming multi-agent reasoning system that significantly reduces latency and improves effectiveness by passing reasoning steps to downstream agents as they are generated, rather than waiting for the entire chain to complete.