Here’s this week’s Ritual Research Digest, a newsletter covering the latest in the world of LLMs and the intersection of Crypto x AI.
With hundreds of papers published weekly, staying current with the latest is impossible. We do the reading so you don’t have to.
DeepSeekMath-V2: Towards Self-Verifiable Mathematical Reasoning
This paper introduces DSMath-V2, a model trained on deepseek-3.2-exp for natural language proving in mathematics. The generation-verification gap is a major hurdle for informal proving.
They first train a verifier for the model using expert annotations to assess both the correctness of the answers and the analysis.
This verifier is used to train the final prover model, which both writes proofs and analyzes their correctness.
They achieve gold in IMO 2025.
Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)
The paper introduces INFINITY-CHAT, a dataset of 26K real-world queries that accept multiple answers. Using this, they study intra- & inter-model mode collapse in 70+ LMs.
They uncover an Artificial Hivemind effect with intra-model repetition, where a model repeatedly generates similar outputs, & inter-model homogeneity, where different models converge on similar ideas with minor phrasing changes. This raises questions about model diversity.
Latent Collaboration in Multi-Agent Systems
The work introduces Latent MAS, an end-to-end collaborative framework that operates in continuous latent space. The design integrates both latent thought generation and cross-agent latent memory transfer.
LatentMAS is based on reasoning expressiveness, communication fidelity and collaboration complexity. Across both sequential and hierarchical MAS settings, Qwen 3(4B, 8B, and 14B), LatentMAS outperforms text-based MAS baselines improving accuracy, & reducing output token usage.
ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration
The authors propose an orchestration paradigm where intelligence emerges from a composite system. An orchestrator model invokes the right tools in right order for a task.
Using ToolOrchestra, an 8B model is trained with RL to decide when and how to invoke other LMs and tools. The rewards balance correctness, efficiency and alignment with user preferences.
On HLE, Orchestrator outperforms prior methods with far lower computational cost.
Follow us @ritualdigest for more on all things crypto x AI research, and
@ritualnet to learn more about what Ritual is building.
516
3
O conteúdo desta página é fornecido por terceiros. A menos que especificado de outra forma, a OKX não é a autora dos artigos mencionados e não reivindica direitos autorais sobre os materiais apresentados. O conteúdo tem um propósito meramente informativo e não representa as opiniões da OKX. Ele não deve ser interpretado como um endosso ou aconselhamento de investimento de qualquer tipo, nem como uma recomendação para compra ou venda de ativos digitais. Quando a IA generativa é utilizada para criar resumos ou outras informações, o conteúdo gerado pode apresentar imprecisões ou incoerências. Leia o artigo vinculado para mais detalhes e informações. A OKX não se responsabiliza pelo conteúdo hospedado em sites de terceiros. Possuir ativos digitais, como stablecoins e NFTs, envolve um risco elevado e pode apresentar flutuações significativas. Você deve ponderar com cuidado se negociar ou manter ativos digitais é adequado para sua condição financeira.