Deep semantic understanding of events requires recognizing related events and distinguishing why an event occurs from how it is carried out. 5W1H extraction provides a structured foundation for such understanding by organizing event information around six fundamental questions. However, single-event slot filling provides limited support for these distinctions. We propose ANCHOR, a cluster-grounded framework that combines a large language model (LLM) with a small language model equipped with discriminative heads for accurate 5W1H extraction. The LLM proposes candidate events and generates their initial 4W records, which guide the selection of an event cluster and the subsequent anchoring of its main event. A shared document encoder provides evidence for joint 4W refinement, and two separate sets of boundary and role-scoring heads then extract why and how under event-specific constraints, respectively. Document representations are reused across events and stages, and unsupported roles can remain empty. Following the same principles, an agent-and-skill annotation workflow constructs a benchmark of 26,110 documents from ten source corpora covering three languages and seven domains. We select nine of the resulting datasets to evaluate ANCHOR against strong baselines using four open-weight LLMs. ANCHOR achieves competitive performance. The datasets and code are available at https://github.com/revolution6575/ANCHOR-5W1H.
Multimodal agents commonly generate free-form reasoning before each action. For small models, limited model capacity can result in lengthy reasoning that provides little useful guidance for action generation while incurring substantial inference cost. To address this challenge, we introduce Selection-based Structured Reasoning (SSR), a framework that reformulates reasoning as selection instead of open-ended generation. SSR represents recurring high-level reasoning as pre-specified, reusable natural-language candidates. At each turn, the model selects from these reasoning candidates based on their likelihoods given the current context, without requiring an auxiliary task head. Using pre-specified reasoning traces enables parallel scoring, where teacher-forced prefilling computes token likelihoods concurrently within and across candidates using a shared context KV cache. We evaluate SSR on seven multimodal search benchmarks using 2B and 4B models. Across multiple reinforcement learning objectives and supervised fine-tuning, SSR delivers significant efficiency gains without sacrificing task performance. SSR achieves an average success rate competitive with leading search agents of the same scale, while reducing per-turn reasoning latency by over 90% and total per-question model inference latency by 28-54%. Project page: https://zfy0314.github.io/ssr-webpage/.