OceanMind: A multi-agent AI system for ocean diagnosis

Real-world Earth observation (EO) agents must translate high-level scientific questions into executable workflows to acquire observations, prepare data, perform domain computations, and derive conclusions from runtime evidence. Existing EO agents typically start from supplied observations, while benchmarks typically provide prepared inputs or candidate answers, leaving full-chain open-world EO execution largely untested. We present Earth-Agent-Pro, an execution-adaptive Plan-and-Execute framework using expert-authored skills to constrain planning and runtime tool use. Workflow-centered structured memory records planned steps, accepted evidence, and their dependencies, enabling repair of only the affected workflow suffix when runtime evidence invalidates a step. Separate large language model adapters use sequence-level supervised fine-tuning for planner workflow composition and node-level group relative policy optimization with locally verifiable rewards for executor tool-argument grounding. Earth-Bench-Pro instantiates 248 expert-curated task cores as 744 questions under three matched regimes. Its 248 Open-World Execution questions span RGB imagery, spectral observations, and remote sensing products, pairing high-level requests with runtime data requirements, executable trajectories, and open-ended answers grounded in execution evidence. With a shared GPT-5 backbone, Earth-Agent-Pro achieves 66.13% LLM-as-Judge accuracy, exceeding ReAct by 20.95 points in this metric and 24.44 points in Tools-In-Order. Joint adapter tuning raises Qwen3.5-9B LLM-as-Judge accuracy from 38.31% to 50.00%, an 11.69-point gain over the untuned configuration. Planning-only evaluation and execution with the reference workflow show that the adapters improve workflow composition and argument grounding, respectively. Code and datasets will be released soon.

Large language models and the agents built on them are the most capable reasoning machines ever built, and science is beginning to put them to work. Atmospheric and oceanic sciences are starting to see agentic integration, but coastal hydrodynamics remains largely untouched by AI. Simply, agents cannot easily read its data products without saturating their context windows. A time frame from a coastal model can hold hundreds of megabytes, and if the archive's chunking does not suit the query, the agent will spend more time downloading and compacting than gaining insights. After all, the archives were designed for storage, not for the fast, on-the-fly access agents need. Speech and music once hit the same wall. A minute of audio is millions of numbers, yet today's audio models hold conversations and write music. They "learned" to do this by "listening" to tokens. Neural audio codecs turn waveforms into short sequences of discrete symbols that a model reads like words and decodes back into sound. Coastal water is a similar signal: dense, finely sampled, and repeatable. We are convinced it has an analogous compact native representation that preserves the salient physics. Tokens are that representation: small integers, light enough for an agent to sweep six months of a coastline in seconds. Agents can then do more than simple lookup-related tasks; they can form and test their hypotheses as they explore the tokenized representation efficiently. Herein, we build this framework, using vector quantized variational autoencoders to compress tide level, the non-tidal residual, and surface wind speed into 16x16 grids of tokens along the US Atlantic and Gulf coasts. Agents traverse and explore these grids (e.g., tracking, spatiotemporal trend analysis) considerably faster than raw archives in both on-prem and off-prem modalities, while correctly answering several types of under-specified queries.

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.