| LLM-Guided Cluster Lifecycle Management: Deciding When and How to Evolve Behavioral ClustersarXiv · authors at Amazon |
Amazon |
Nov 2026 |
0 |
931 |
| Compiling Known Rules into Compact Neural Agents: Weight-Space Programming on Unseen GamesarXiv · authors at Amazon |
Amazon |
Nov 2026 |
0 |
931 |
| DecArena: Evaluating Large-Scale Decentralized Multi-Agent CollaborationarXiv · authors at Amazon |
Amazon |
Nov 2026 |
0 |
931 |
| Vocabulary-Free Next-Event Prediction on Temporal GraphsarXiv · authors at Amazon |
Amazon |
Nov 2026 |
0 |
931 |
| Comparative Analysis of Agent Evaluation Frameworks: Stability, Detection, and Discovery in Enterprise Analytics AgentsarXiv · authors at Amazon |
Amazon |
Nov 2026 |
0 |
931 |
| Code-Grounded Agentic Explanations for Static Analysis Vulnerability FindingsarXiv · authors at Amazon |
Amazon |
Nov 2026 |
0 |
931 |
| Which Successes Make Good References? Action-Sequence Alignment for Multi-Turn On-Policy DistillationarXiv · authors at Amazon |
Amazon |
Nov 2026 |
0 |
931 |
| Query-Guided RoPE Modulation for Lost-in-the-Middle Mitigation in Long-Context LLMsarXiv · authors at Amazon |
Amazon |
Nov 2026 |
0 |
931 |
| Householder Motion Embedding: Noise Modulation for Motion-Controllable Video GenerationarXiv · authors at Amazon |
Amazon |
Nov 2026 |
0 |
931 |
| FARR: Forecast-Aware Residual Refinement with Matched Endpoint Evidence for Long-Horizon Time-Series ForecastingarXiv · authors at Amazon |
Amazon |
Nov 2026 |
0 |
931 |
| Latent RL Priors for Data-Efficient Dexterous ManipulationarXiv · authors at Amazon |
Amazon |
Nov 2026 |
0 |
931 |
| zkARc: Succinctly Verifiable Proofs for Neurosymbolic Natural Language Formalization and VerificationarXiv · authors at Amazon |
Amazon |
Nov 2026 |
0 |
931 |
| From Handcrafted to Generative: RLVR-Optimized Icon Generation for Alexa+arXiv · authors at Amazon |
Amazon |
Nov 2026 |
0 |
931 |
| Koopman Generative Operators for Efficient Probabilistic Time-Series ForecastingarXiv · authors at Amazon |
Amazon |
Nov 2026 |
0 |
931 |
| PATTS: Parallel-Aware Test-Time Scaling for Thought-Image Generation in Multimodal Discrete Diffusion LLMsarXiv · authors at Amazon |
Amazon |
Nov 2026 |
0 |
931 |
| Route to Remember: Adaptive Memory Selection for LLM AgentsarXiv · authors at Amazon |
Amazon |
Nov 2026 |
0 |
931 |
| Sundance: A Simple SMT Solver for Program VerificationarXiv · authors at Amazon |
Amazon |
Nov 2026 |
0 |
931 |
| Cognitive Bias Signatures in Search-Equipped LLM Agents: A Stage-Resolved AnalysisarXiv · authors at Amazon |
Amazon |
Nov 2026 |
0 |
931 |
| Energy-Based Policy OrchestrationarXiv · authors at Amazon |
Amazon |
Nov 2026 |
0 |
931 |
| WASP-Mem: Let Agent Organize Procedural Memory. Human Spend Effort on DiagnosisarXiv · authors at Amazon |
Amazon |
Nov 2026 |
0 |
931 |
| Scaling Lean Theorem Proving for Real-World Code Verificationlisted by Amazon on Hugging Face |
Amazon |
Oct 2026 |
0 |
931 |
| Lean4AgenticRL: Advancing Agentic RL with Verifiable Multi-level Process Rewardslisted by Amazon on Hugging Face |
Amazon |
Oct 2026 |
0 |
931 |
| ANTE: Anticipate, Then Execute -- Learning Internal World Models for Coding Agents from Verified Beliefslisted by Amazon on Hugging Face |
Amazon |
Oct 2026 |
0 |
931 |
| ALoDLM: Adaptively Looped Diffusion Language Modelslisted by Amazon on Hugging Face |
Amazon |
Oct 2026 |
0 |
931 |
| Training LLM Judges from Language Feedback via Position-Selective Self-Distillationlisted by Amazon on Hugging Face |
Amazon |
Sep 2026 |
0 |
931 |
| Hermes: Learning Contextual Reasoning Unlocks Test-Time Scalinglisted by Amazon on Hugging Face |
Amazon |
Sep 2026 |
0 |
931 |
| MILO: Automated Harness Discovery via Orchestrated Multi-Agent Evolutionlisted by Amazon on Hugging Face |
Amazon |
Sep 2026 |
0 |
931 |
| On the Off-Policy Teacher in On-Policy Distillationlisted by Amazon on Hugging Face |
Amazon |
Sep 2026 |
0 |
931 |
| Breaking Babel: A Self-Evolving Multi-Agent System for Long-Form Subtitle Translationlisted by Amazon on Hugging Face |
Amazon |
Sep 2026 |
0 |
931 |
| Rethinking Latent Visual Reasoning: Grounding Latent Reasoning in Visual Evidencelisted by Amazon on Hugging Face |
Amazon |
Sep 2026 |
0 |
931 |
| StructRL: Online Structured Reinforcement Learning for Long-Horizon Vision-Language-Action Taskslisted by Amazon on Hugging Face |
Amazon |
Sep 2026 |
0 |
931 |
| LEGO-Anything: Coding Agents for 3D Scene Reconstructionlisted by Amazon on Hugging Face |
Amazon |
Sep 2026 |
0 |
931 |
| Rufus-Air: An Open LLM Post-Training Recipelisted by Amazon on Hugging Face |
Amazon |
Sep 2026 |
0 |
931 |
| AutoResearch at Production Scale: Failure Modes and a Multi-Agent Frameworklisted by Amazon on Hugging Face |
Amazon |
Sep 2026 |
0 |
931 |
| Don't Mask the Environment: Observation Supervision Changes How Agents Explore Under RLlisted by Amazon on Hugging Face |
Amazon |
Sep 2026 |
0 |
931 |
| MInTRL: Off-policy Intervention can boost On-policy RLlisted by Amazon on Hugging Face |
Amazon |
Sep 2026 |
0 |
931 |
| Beyond Solver Verdicts: Generative Reward Models for Autoformalizationlisted by Amazon on Hugging Face |
Amazon |
Sep 2026 |
0 |
931 |
| Group Adaptive Clipping Policy Optimizationlisted by Amazon on Hugging Face |
Amazon |
Aug 2026 |
0 |
931 |
| Training Leaves Traces: Centered Residual Signatures for Language Model Lineage Verificationlisted by Amazon on Hugging Face |
Amazon |
Aug 2026 |
0 |
931 |
| TrajLoc: Trajectory-Attention Localization for Multi-Object Motion Controllisted by Amazon on Hugging Face |
Amazon |
Jun 2026 |
0 |
931 |
| When LLMs Read Tables Carelessly: Measuring and Reducing Data Referencing Errorslisted by Amazon on Hugging Face |
Amazon |
Jun 2026 |
0 |
931 |
| Statistically Reliable LLM-Based Ranking Evaluation via Prediction-Powered Inferencelisted by Amazon on Hugging Face |
Amazon |
Jun 2026 |
0 |
931 |
| Learning to Optimize Multi-Objective Alignment Through Dynamic Reward WeightingTransactions of the Association for Computational Linguistics · authors at Amazon |
Amazon |
Jun 2026 |
38 |
931 |
| Adaptive Auto-Harness: Sustained Self-Improvement for Agentic System Deployment on Open-Ended Task StreamsarXiv · authors at Amazon |
Amazon |
Jun 2026 |
38 |
931 |
| An Empirical Study of Automating Agent Evaluationlisted by Amazon on Hugging Face |
Amazon |
May 2026 |
0 |
931 |
| Emergent Strategic Reasoning Risks in AI: A Taxonomy-Driven Evaluation Frameworklisted by Amazon on Hugging Face |
Amazon |
Apr 2026 |
0 |
931 |
| Expert Upcycling: Shifting the Compute-Efficient Frontier of Mixture-of-Expertslisted by Amazon on Hugging Face |
Amazon |
Apr 2026 |
0 |
931 |
| A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokenslisted by Amazon on Hugging Face |
Amazon |
Apr 2026 |
0 |
931 |
| Perceptio: Perception Enhanced Vision Language Models via Spatial Token Generationlisted by Amazon on Hugging Face |
Amazon |
Mar 2026 |
0 |
931 |
| Scalable Prompt Routing via Fine-Grained Latent Task Discoverylisted by Amazon on Hugging Face |
Amazon |
Mar 2026 |
0 |
931 |
| Supervised Fine-Tuning versus Reinforcement Learning: A Study of Post-Training Methods for Large Language Modelslisted by Amazon on Hugging Face |
Amazon |
Mar 2026 |
0 |
931 |
| ByteFlow: Language Modeling through Adaptive Byte Compression without a Tokenizerlisted by Amazon on Hugging Face |
Amazon |
Mar 2026 |
0 |
931 |
| Reinforcement-aware Knowledge Distillation for LLM Reasoninglisted by Amazon on Hugging Face |
Amazon |
Feb 2026 |
0 |
931 |
| DREAM: Deep Research Evaluation with Agentic Metricslisted by Amazon on Hugging Face |
Amazon |
Feb 2026 |
0 |
931 |
| DODO: Discrete OCR Diffusion Modelslisted by Amazon on Hugging Face |
Amazon |
Feb 2026 |
0 |
931 |
| DDiT: Dynamic Patch Scheduling for Efficient Diffusion Transformerslisted by Amazon on Hugging Face |
Amazon |
Feb 2026 |
0 |
931 |
| Approximation of Log-Partition Function in Policy Mirror Descent Induces Implicit Regularization for LLM Post-Traininglisted by Amazon on Hugging Face |
Amazon |
Feb 2026 |
0 |
931 |
| SpIDER: Spatially Informed Dense Embedding Retrieval for Software Issue Localizationlisted by Amazon on Hugging Face |
Amazon |
Feb 2026 |
0 |
931 |
| An Introduction to Input/Output AutomataFormal Aspects of Computing · authors at Amazon |
Amazon |
Jan 2026 |
1,021 |
931 |
| VERGE: Formal Refinement and Guidance Engine for Verifiable LLM Reasoninglisted by Amazon on Hugging Face |
Amazon |
Jan 2026 |
0 |
931 |
| LikeBench: Evaluating Subjective Likability in LLMs for Personalizationlisted by Amazon on Hugging Face |
Amazon |
Dec 2025 |
0 |
931 |
| Monet: Reasoning in Latent Visual Space Beyond Images and LanguagearXiv · authors at Amazon |
Amazon |
Nov 2025 |
78 |
931 |
| WebCoach: Self-Evolving Web Agents with Cross-Session Memory Guidancelisted by Amazon on Hugging Face |
Amazon |
Nov 2025 |
0 |
931 |
| Experience-Guided Adaptation of Inference-Time Reasoning Strategieslisted by Amazon on Hugging Face |
Amazon |
Nov 2025 |
0 |
931 |
| TritonRL: Training LLMs to Think and Code Triton Without CheatingarXiv · authors at Amazon |
Amazon |
Oct 2025 |
34 |
931 |
| Context Length Alone Hurts LLM Performance Despite Perfect RetrievalarXiv · authors at Amazon |
Amazon |
Oct 2025 |
128 |
931 |
| ResMimic: From General Motion Tracking to Humanoid Whole-body Loco-Manipulation via Residual LearningarXiv · authors at Amazon |
Amazon |
Oct 2025 |
103 |
931 |
| A CLIP-based Uncertainty Modal Modeling (UMM) Framework for Pedestrian Re-Identification in Autonomous DrivingArtificial intelligence technology research. · authors at Amazon |
Amazon |
Jul 2025 |
44 |
931 |
| Scalable, Validated Code Translation of Entire Projects using Large Language ModelsProceedings of the ACM on Programming Languages · authors at Amazon |
Amazon |
Jun 2025 |
73 |
931 |
| CTLformer: A Hybrid Denoising Model Combining Convolutional Layers and Self-Attention for Enhanced CT Image ReconstructionApplied and Computational Engineering · authors at Amazon |
Amazon |
May 2025 |
43 |
931 |
| Griffin: Towards a Graph-Centric Relational Database Foundation ModelarXiv · authors at Amazon |
Amazon |
May 2025 |
38 |
931 |
| AgentA/B: Automated and Scalable Web A/BTesting with Interactive LLM AgentsarXiv · authors at Amazon |
Amazon |
Apr 2025 |
42 |
931 |
| SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language ModelsTransactions on machine learning research · authors at Amazon |
Amazon |
Apr 2025 |
273 |
931 |
| Stepwise Perplexity-Guided Refinement for Efficient Chain-of-Thought Reasoning in Large Language ModelsarXiv · authors at Amazon |
Amazon |
Feb 2025 |
68 |
931 |
| Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and BeyondarXiv · authors at Amazon |
Amazon |
Feb 2025 |
79 |
931 |
| A multimodal multidomain multilingual medical foundation model for zero shot clinical diagnosisnpj Digital Medicine · authors at Amazon |
Amazon |
Feb 2025 |
62 |
931 |
| AI-Driven Security in Cloud Computing: Enhancing Threat Detection, Automated Response, and Cyber ResilienceSSRN Electronic Journal · authors at Amazon |
Amazon |
Jan 2025 |
39 |
931 |