DOVA: Deliberation-First Multi-Agent Orchestration for Autonomous Research Automation
This addresses the problem of inefficient and limited reasoning in AI research automation for users needing multi-source synthesis and verification, though it appears incremental as it builds on existing multi-agent concepts.
The paper tackles the limitations of single-agent LLM systems in complex research tasks by introducing DOVA, a multi-agent platform with deliberation-first orchestration and adaptive thinking, achieving a 40-60% reduction in inference cost on simple tasks while maintaining reasoning capacity.
Large language model (LLM) agents have demonstrated remarkable capabilities in tool use, reasoning, and code generation, yet single-agent systems exhibit fundamental limitations when confronted with complex research tasks demanding multi-source synthesis, adversarial verification, and personalized delivery. We present DOVA (Deep Orchestrated Versatile Agent), a multi-agent platform introducing three key innovations: (1) deliberation-first orchestration, where explicit meta-reasoning precedes tool invocation, informed by a persistent user model and entity-aware conversation context; (2) hybrid collaborative reasoning, a composable three-phase pipeline unifying ensemble diversity, blackboard transparency, and iterative refinement; and (3) adaptive multi-tiered thinking, a six-level token-budget allocation scheme that reduces inference cost by 40-60% on simple tasks while preserving deep reasoning capacity. We formalize the core algorithms, present an architectural ablation study across seven system configurations, and analyze the contribution of each component to answer confidence, source coverage, and token efficiency.