MLINFO COLLECTION
検索拡張生成、文書検索、社内ナレッジQAに関係する論文・実装をまとめます。
Multi-agent systems often rely on predefined collaboration structures, limiting their ability to adapt to diverse task requirements. We introduce DynaFlow, a framework that integrates free-form…
In this paper, we introduce Δτ-Bench, an executable agent benchmark that models the structural evolution of large tool ecosystems. In Δτ-Bench, independently evolving services continually reshape how…
Deploying language agents in real applications demands more than the right answer: an agent must execute a multi-step business process correctly, follow domain-specific rules, and interact with a…
As model parameters scale up, sparsely activated Mixture-of-Experts (MoE) approaches have become essential for model scaling. However, mainstream models currently adopt hierarchical architectures,…
Video captioning aims to preserve visual information through compact descriptions, predominantly using natural language. However, precisely expressing fine-grained spatial structures and temporal…
Recursive self-improvement (RSI), in which a system also improves the way it improves, is a long-standing aspiration on the path to AGI. Language agents increasingly store procedural knowledge in…
While progress in informal mathematics has come largely from scaling the chain-of-thought and agentic reasoning of frontier language models, formal theorem proving has increasingly relied on…
Voice style conversion (VSC) aims to transform a source utterance to match the timbre, accent, and emotion of a target voice while preserving linguistic content. StyleStream 1.0 introduced the first…
In this report, we introduce Sage-A1.5, a 35B Mixture-of-Experts agentic model that builds on A1 to advance long-horizon problem solving through adaptive capability composition. Compared with A1,…
Cooperative language-model agents can improve without weight updates by revising reusable skills, but only if a shared team reward is traced to the responsible agent and skill. Existing methods…
Tool-using voice agents often leave users waiting after speech ends, even when actionable information arrives earlier in the request. Speculative approaches begin work during speech, but…
We propose Nemotron-Labs-Diffusion-Uni (NLD-Uni), a unified discrete diffusion large language model (DLLM) for visual understanding and generation tasks. Compared with prior unified diffusion models,…
Continual learning is the ability of LLM agents to improve over time by acquiring, refining, and applying knowledge from experience while retaining useful prior knowledge. It is essential for agents…
Explore concepts like Self-Correct, Self-Refine, Self-Improve, Self-Contradict, Self-Play, and Self-Knowledge, alongside o1-like reasoning elevation🍓 and hallucination alleviation🍄.
A benchmark is not merely a collection of test questions; it naturally induces an empirical measure over difficulty. In this work, we develop this measure-based view of benchmark evaluation.
Brain encoding models aim to predict neural responses to stimuli. The most widely used approach fits readouts from frozen pretrained backbones.
Lifelong agents continually accumulate and reuse experience to improve after deployment, yet in practice they often operate under tight generation, interaction, and memory budgets. Under such…
Long-video generators increasingly retrieve past visual observations to prevent identity drift. The intuition is compelling: more access to history should make future video more consistent.
Outcome RL raises pass@1 but not pass@k at large k (Yue et al., 2025). But every pass@1 is scored under a token budget.
Generative models increasingly expose a reasoning effort setting that lets users scale inference-time compute, trading higher cost for potentially improved performance. Users must choose an effort…
Scaling vision-language-action (VLA) models is constrained by scarce action-labeled demonstrations and incompatible control spaces across robot embodiments. We present RynnVLA-Latent, a framework…
Precise camera control is essential for cinematic character video generation, yet existing methods struggle to follow large-angle trajectories with combined rotation, translation, and radius…
We introduce RynnUnify, a 16B unified embodied model that combines strong embodied understanding with long-horizon visual planning through interleaved video--language reasoning. With capabilities…
Spatial intelligence requires agents to actively acquire visual evidence and integrate observations into a coherent representation of the three-dimensional world. Yet spatial question answering…