Papersby GlyphGoogle research papers
A company publishing mostly on agents and evaluation, best known here for Attention Is All You Need.45 papers · 355,125 citations · latest Oct 2026
EmbeddingGemma 2: Unified and Efficient Multimodal RepresentationsEmbeddingGemma 2 is an open multimodal embedding model that unifies text, images, audio, and video representations with efficient resource-flexible design and state-of-the-art benchmark performance.
Google34 upvotesRead →StreamVibe: Proactive Video Agents for Evolving User IntentStreamVibe introduces a benchmark, streaming vision-language model, and hierarchical memory harness to enable proactive, intent-aware interaction with implicit and evolving user goals.Google78 upvotesRead →On-Policy Self-Training: Data-Free Self-Improvement in Large Language ModelsFoundation models can self-improve across text and vision tasks by generating synthetic questions and reasoning traces guided only by high-level topics, without external supervision.Google31 upvotesRead →DeLoop: Repeated Actions as Self-Supervision for Long-Horizon AgentsThis self-supervised training method teaches AI agents to avoid repetitive, unproductive actions during long tasks by using their own history as feedback.Google21 upvotesRead →CLASHarness: Benchmarking Multi-Agent Conflict in Computer Use via a Controllable and Verifiable Generation PipelineThis paper introduces a benchmark and generation pipeline to evaluate how agents resolve conflicts and verify information in multi-agent computer-use scenarios.Google36 upvotesRead →Harness^2: Recursive Agent Harnessing for an Open WorldThis paper introduces a recursive framework that allows agents to automatically improve their own execution harnesses for better performance on novel open-world tasks.Google2 citations123 upvotesRead →VIS-Ground: Video Interactive Storytelling with Contextual GroundingThis paper introduces a framework that transforms heterogeneous user inputs into structured constraints to improve grounding in interactive video generation.Google103 upvotesRead →SEER: Self-Evolving Event Reasoning and Retrieval for Time Series ForecastingSEER improves time series forecasting by using a closed-loop system to retrieve and reason about external events that influence data trends.Google35 upvotesRead →RPTune: Learned Context Curation for LLM Catalog SearchRPTune improves LLM search accuracy by learning how to curate product catalogs and adapting the model to those curated contexts.Google40 upvotesRead →VeriHarness: Scaling Agentic Verification for Long-Horizon TasksVeriHarness improves long-horizon agent performance by using the base model as a verifier to resolve conflicting claims and challenge consensus.Google1 citations62 upvotesRead →AIM: Agentic Idea Management for Automated ResearchAIM is an autonomous framework that manages and explores research directions by using surrogate models to guide experimental budget allocation.Google2 citations53 upvotesRead →Selecting Diverse SFT Traces Improves Post-RL GeneralizationSelecting diverse reasoning paths during supervised fine-tuning improves model performance and generalization after reinforcement learning.Google38 upvotesRead →RRSI: Regularized Recursive Self-Improvement of Agent HarnessesRRSI keeps self-improving agent harnesses from memorising their training tasks, so gains carry over to new benchmarks.Google32 citations221 upvotesRead →Verifiable Social Reasoning for LLM AssistantsFuse is a multi-agent simulation framework that allows for the verifiable evaluation of an assistant's social reasoning capabilities.Google2 citations67 upvotesRead →Dream-RSI: Recursive Self-Improvement through Evolving WorldsDream-RSI enables scalable recursive self-improvement by using historical discovery replay to evaluate exploration policies offline, reducing costly online evaluations.Google24 citations246 upvotesRead →Procedural Graphs: Self-Evolving Execution Structures for LLM AgentsA procedural graph framework organizes agent actions into structured relational triplets, providing situational guidance and self-evolving topology to improve long-horizon tool use.Google2 citations41 upvotesRead →WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill EvolutionWikiSkill co-evolves reusable agent skills with a persistent knowledge base to systematically accumulate experience and improve performance across models.Google23 citations34 upvotesRead →EnvHarness: Awakening Static Worlds for Agent LearningEnvHarness and EnvRigger dynamically reshape static environments via programmable plugins to target agent weaknesses and improve reinforcement learning co-evolution.Google19 citations174 upvotesRead →Concurrent Image Understanding and Generation: Self-Correcting Coupled Markov Jump ProcessesA coupled Markov jump process with cross-modal attention and remasking enables a training-free single-pass sampler for joint multimodal generation that improves with more denoising steps.Google1 citations29 upvotesRead →Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMsReinforcement learning with metacognitive feedback and metacognitive data selection improve large language model calibration by enabling accurate self-assessment of performance and uncertainty.Google3 citations28 upvotesRead →FLAT: Feedforward Latent Triangle Splatting for Geometrically Accurate Scene GenerationVideo diffusion models are adapted to decode explicit surface primitives directly from latent space, enabling high-quality 3D scene generation with improved geometric accuracy and real-time rendering capabilities.Google1 citations26 upvotesRead →From AGI to ASIArtificial general intelligence development may lead to artificial general superintelligence through multiple pathways, requiring interdisciplinary global preparation for transformative societal changes.Google9 citations39 upvotesRead →Language Models Need Sleep: Learning to Self-Modify and Consolidate MemoriesDeep learning models with sleep and dreaming paradigms enable continual learning through memory consolidation and self-improvement phases.Google9 citations28 upvotesRead →ScientistOne: Towards Human-Level Autonomous Research via Chain-of-EvidenceAutonomous research agents exhibit verifiability issues like fabricated citations and unreproducible results, which are addressed through a framework ensuring evidence traceability and an end-to-end system maintaining integrity throughout research processes.Google21 citations35 upvotesRead →Sensor2Sensor: Cross-Embodiment Sensor Conversion for Autonomous DrivingSensor2Sensor generates high-fidelity multi-modal sensor data from in-the-wild dashcam videos using diffusion models and 4D Gaussian Splatting for autonomous driving system training and validation.Google3 citations25 upvotesRead →TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D TrackingTrackCraft3R enables efficient dense 3D tracking from monocular video by adapting video diffusion transformers to follow physical points across frames using dual-latent representation and temporal RoPE alignment.Google8 citations37 upvotesRead →RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable RewardsDeep research agents trained using RubricEM framework demonstrate superior performance on long-form research tasks through rubric-guided reinforcement learning with stage-aware planning and reflection-based meta-policy evolution.Google16 citations77 upvotesRead →LLMs Improving LLMs: Agentic Discovery for Test-Time ScalingAutoTTS automates test-time scaling strategy discovery by formulating it as controller synthesis over reasoning trajectories and probe signals, achieving improved accuracy-cost tradeoffs with minimal computational overhead.Google8 citations70 upvotesRead →VGGRPO: Towards World-Consistent Video Generation with 4D Latent RewardVGGRPO enhances video diffusion models with latent geometry guidance to improve geometric consistency and camera stability while avoiding expensive VAE decoding.Google28 citations64 upvotesRead →Thinking to Recall: How Reasoning Unlocks Parametric Knowledge in LLMsReasoning in large language models enhances parametric knowledge recall through computational buffer and factual priming mechanisms, though it carries risks of hallucination that can be mitigated by prioritizing accurate reasoning trajectories.Google17 citations76 upvotesRead →Unified Latents (UL): How to train your latentsUnified Latents framework learns joint latent representations using diffusion prior regularization and diffusion model decoding, achieving competitive FID scores with reduced training compute.Google19 citations63 upvotesRead →Towards Autonomous Mathematics ResearchAletheia, a math research agent, demonstrates advanced reasoning capabilities by generating and verifying solutions end-to-end in natural language, achieving autonomous research outcomes from Olympiad problems to PhD-level exercises and contributing to AI-assisted mathematical research.Google39 citations36 upvotesRead →Reinforced Attention LearningReinforced Attention Learning optimizes internal attention distributions in multimodal language models, improving information allocation and cross-modal alignment through policy-gradient methods.Google8 citations30 upvotesRead →MARS: Modular Agent with Reflective Search for Automated AI ResearchMARS is a modular AI research automation framework that uses budget-aware planning, modular construction, and reflective memory to achieve state-of-the-art performance in autonomous machine learning research.Google31 citations67 upvotesRead →PaperBanana: Automating Academic Illustration for AI Scientists_paperbanana is an agentic framework that automates the creation of publication-ready academic illustrations using advanced vision-language models and image generation techniques.Google36 citations230 upvotesRead →Alterbute: Editing Intrinsic Attributes of Objects in ImagesAlterbute presents a diffusion-based approach for editing object intrinsic attributes while preserving identity and context through relaxed training objectives and visual named entities for scalable supervision.Google31 upvotesRead →Emergent temporal abstractions in autoregressive models enable hierarchical reinforcement learningThis paper shows that autoregressive models can learn temporally-abstract actions within their internal representations to enable efficient hierarchical reinforcement learning.Google5 citations62 upvotesRead →Efficiently Reconstructing Dynamic Scenes One D4RT at a TimeD4RT, a unified transformer-based model, efficiently reconstructs 4D scenes from videos by querying 3D positions in space-time, outperforming previous methods.Google74 citations25 upvotesRead →Budget-Aware Tool-Use Enables Effective Agent ScalingBudget-aware methods improve the scaling of tool-augmented agents by providing continuous budget awareness and adaptive planning, leading to better cost-performance trade-offs.Google61 citations34 upvotesRead →Supervised Reinforcement Learning: From Expert Trajectories to Step-wise ReasoningSupervised Reinforcement Learning (SRL) enhances small-scale LLMs' multi-step reasoning by generating internal monologues and using step-wise expert actions for richer learning signals, outperforming SFT and RLVR.Google12 citations48 upvotesRead →CoDA: Agentic Systems for Collaborative Data VisualizationCoDA, a multi-agent system using specialized LLM agents, enhances visualization automation by managing data complexity and ensuring high-quality visualizations through collaborative workflows.Google16 citations32 upvotesRead →Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic CapabilitiesGemini 2.X model family, including Gemini 2.5 Pro and Flash, offers superior coding, reasoning, and multimodal understanding capabilities across a range of computational efficiencies.Google4,594 citations67 upvotesRead →Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsAsking a model to write out its intermediate steps (chain of thought) sharply improves its math and logic answers.Google23.8k citations16 upvotesRead →BERT: Pre-training of Deep Bidirectional Transformers for Language UnderstandingPre-training a Transformer to fill in masked words, then fine-tuning it, beat task-specific models across language understanding tests.Google125k citations33 upvotesRead →Attention Is All You NeedIntroduced the Transformer, the attention-only architecture behind nearly every large language model since.Google201k citations142 upvotesRead →
About and links
Topics: Agents and evaluation 15, Multimodal and robotics 9, Training and scaling 5, Reasoning 5, Foundation models 4, Applied AI 2, Retrieval and data 2, Inference and efficiency 1, Alignment and safety 1, Architectures 1
Google lab profile on Labs (labs.fru.dev): leaders, models, landmarksGoogle on Companies (companies.fru.dev)Also onAcquisitions·Paydays·TechConf·Releases