Skip to main content
Search

# MIRROR

4 related articles

Subscribe to updates
  1. reflection.ai

    Reflection opens 501B-parameter Beam weights under Apache 2.0, with 40-plus partners turning one model into a self-hostable stack

    Reflection released Beam, its first open-weight model, with 501 billion total parameters and 23 billion active in a sparse Mixture-of-Experts design for coding, reasoning and long-horizon agentic workloads, publishing weights on Hugging Face under Apache 2.0 with a model card and a safety technical report. Where an open-weight release usually delivers one model layer, this one also ships BF16, FP8 and NVFP4 precision formats, a speculative decoding drafter, and integrations from more than 40 partners across inference, fine-tuning, deployment and agent harnesses, so developers can download, self-host and customize it for their own domains.

    reflection.ai
    BeamMixture-of-ExpertsMIRRORReinforcement Learning
  2. reflection.ai

    Reflection opens Beam weights: 501B-parameter sparse MoE, 23B active, Apache 2.0 self-hosting

    Reflection released the weights of Beam, its first open-weight model, on Hugging Face under an Apache 2.0 license; Beam is a sparse Mixture-of-Experts model with 501 billion total parameters and 23 billion active, built for coding, reasoning, and long-horizon agentic workloads. Previously the model was reachable only through Reflection and its partners, and developers can now download and self-host it, evaluate it, and customize it for their own domains. The release ships with final benchmarks in the model card and a safety technical report, plus an ecosystem of over 40 partners and integrations spanning inference, quantization, fine-tuning, reinforcement learning, agent harnesses, evaluation, and observability, which Reflection calls an open operating system for agents.

    BeamOpen-weight model releaseMixture of ExpertsMIRROR
  3. arXiv

    MIRROR turns LLM personalization from imitation to preference internalization via reference-revealed on-policy self-distillation, leading three benchmarks with less forgetting

    MIRROR treats a user's reference text as hindsight information and aligns the model's next-token distributions along its own on-policy trajectories with those of its reference-conditioned self, internalizing preferences instead of copying wording; MIRROR-F adds selective anchoring on informative, context-grounded reference tokens. Across three personalized generation benchmarks, two model scales, and reference-based plus LLM-judge evaluations, both achieve leading personalization and text quality with less forgetting than SFT baselines on three unseen tasks.

    Baidu (China)
    Huayi Lai（First author）
    MIRRORMIRROR-FOn-Policy Self-DistillationLLM PersonalizationPersonalized Text Generation
  4. arXiv

    MIRROR cuts agent-in-the-middle attack success to 0% in LLM multi-agent communication via multipath quorum integrity

    MIRROR is a communication-layer integrity primitive that replicates a single canonicalized payload across k logical routes and accepts a message only when a strict majority of routes report the same digest; under a route-compromise bound of alpha < 0.5, it reduces attack success rate to 0% across MMLU, HumanEval, and MBPP on two frameworks and four topologies and in a MetaGPT deployment against a production API, at 1x LLM token cost, whereas LLM-as-a-Judge costs 35x in the same deployment and blocks up to 44.2% of benign outputs in the topology sweep.

    University of Southern California
    Ryuichi Yamafuji Lun（First author）
    MIRRORMultipath Quorum IntegrityAgent-in-the-Middle attacksmulti-agent systems

You’re all caught up