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.
923
4
The content on this page is provided by third parties. Unless otherwise stated, OKX is not the author of the cited article(s) and does not claim any copyright in the materials. The content is provided for informational purposes only and does not represent the views of OKX. It is not intended to be an endorsement of any kind and should not be considered investment advice or a solicitation to buy or sell digital assets. To the extent generative AI is utilized to provide summaries or other information, such AI generated content may be inaccurate or inconsistent. Please read the linked article for more details and information. OKX is not responsible for content hosted on third party sites. Digital asset holdings, including stablecoins and NFTs, involve a high degree of risk and can fluctuate greatly. You should carefully consider whether trading or holding digital assets is suitable for you in light of your financial condition.