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.
948
4
O conteúdo apresentado nesta página é fornecido por terceiros. Salvo indicação em contrário, a OKX não é o autor dos artigos citados e não reivindica quaisquer direitos de autor nos materiais. O conteúdo é fornecido apenas para fins informativos e não representa a opinião da OKX. Não se destina a ser um endosso de qualquer tipo e não deve ser considerado conselho de investimento ou uma solicitação para comprar ou vender ativos digitais. Na medida em que a IA generativa é utilizada para fornecer resumos ou outras informações, esse mesmo conteúdo gerado por IA pode ser impreciso ou inconsistente. Leia o artigo associado para obter mais detalhes e informações. A OKX não é responsável pelo conteúdo apresentado nos sites de terceiros. As detenções de ativos digitais, incluindo criptomoedas estáveis e NFTs, envolvem um nível de risco elevado e podem sofrer grandes flutuações. Deve considerar cuidadosamente se o trading ou a detenção de ativos digitais é adequado para si à luz da sua condição financeira.