Bridging Perception, Behavior, and Interaction Reasoning in Roadside Traffic Scenes

Urban traffic scenes involve dynamic multi-agent behaviors and interactions, yet existing roadside benchmarks emphasize agent-level perception or holistic event reasoning, leaving behavior evolution and multi-agent interactions insufficiently modeled and evaluated. We introduce TRACE-Bench, a benchmark for roadside Traffic Reasoning through Agent-Centric Evolution. TRACE-Bench adopts a hierarchical annotation framework linking scene context, agent perception, behavior evolution, directed interactions, and causal reasoning. Continuous agent motion is decomposed into temporally grounded behavior units, while interactions are represented as directed influence–response relations. Built from real-world roadside RGB-Event recordings, TRACE-Bench comprises 201 finely annotated video sequences and 22,807 evidence-grounded QA pairs. We further propose an Event-Guided Sparse Multimodal framework that progressively reduces redundancy and fuses complementary RGB-Event information for efficient fine-grained traffic reasoning. Extensive experiments reveal limitations of existing MLLMs in behavior understanding and interaction reasoning, while demonstrating that our framework improves traffic perception and understanding with reduced inference latency.