{"total":86,"rows":[{"id":"2601.20802","title":"Reinforcement Learning via Self-Distillation","created":"2026-01-28","cited_by_count":332,"area":"lr"},{"id":"2601.19897","title":"Self-Distillation Enables Continual Learning","created":"2026-01-27","cited_by_count":247,"area":"offlinerl"},{"id":"2507.07957","title":"MIRIX: Multi-Agent Memory System for LLM-Based Agents","created":"2025-07-10","cited_by_count":173,"area":"agents"},{"id":"2512.24695","title":"Nested Learning: The Illusion of Deep Learning Architectures","created":"2025-12-31","cited_by_count":72,"area":null},{"id":"2510.03215","title":"Cache-to-Cache: Direct Semantic Communication Between Large Language Models","created":"2025-10-03","cited_by_count":61,"area":"inference"},{"id":"2602.02482","title":"Expanding the Capabilities of Reinforcement Learning via Text Feedback","created":"2026-02-02","cited_by_count":53,"area":"alignment"},{"id":"2602.15902","title":"Doc-to-LoRA: Learning to Instantly Internalize Contexts","created":"2026-02-13","cited_by_count":43,"area":"lr"},{"id":"2603.12273","title":"Aligning Language Models from User Interactions","created":"2026-02-18","cited_by_count":28,"area":"alignment"},{"id":"2512.20237","title":"MemR$^3$: Memory Retrieval via Reflective Reasoning for LLM Agents","created":"2025-12-23","cited_by_count":19,"area":"lr"},{"id":"2606.05661","title":"Continual Learning Bench: Evaluating Frontier AI Systems in Real-World Stateful Environments","created":"2026-06-04","cited_by_count":17,"area":null},{"id":"2510.02375","title":"Pretraining with hierarchical memories: separating long-tail and common knowledge","created":"2025-09-29","cited_by_count":14,"area":null},{"id":"2511.01815","title":"KV Cache Transform Coding for Compact Storage in LLM Inference","created":"2025-11-03","cited_by_count":13,"area":"inference"},{"id":"2606.23525","title":"Self-Compacting Language Model Agents","created":"2026-06-22","cited_by_count":11,"area":"agents"},{"id":"2512.14946","title":"EVICPRESS: Joint KV-Cache Compression and Eviction for Efficient LLM Serving","created":"2025-12-16","cited_by_count":10,"area":"inference"},{"id":"2510.16932","title":"Prompt-MII: Meta-Learning Instruction Induction for LLMs","created":"2025-10-19","cited_by_count":9,"area":null},{"id":"2603.13875","title":"GradMem: Learning to Write Context into Memory with Test-Time Gradient Descent","created":"2026-03-14","cited_by_count":9,"area":null},{"id":"2512.21720","title":"An Information Theoretic Perspective on Agentic System Design","created":"2025-12-25","cited_by_count":8,"area":"agents"},{"id":"2602.08382","title":"Dynamic Long Context Reasoning over Compressed Memory via End-to-End Reinforcement Learning","created":"2026-02-09","cited_by_count":8,"area":"lr"},{"id":"2603.01761","title":"Position: Modular Memory is the Key to Continual Learning Agents","created":"2026-03-02","cited_by_count":8,"area":"lr"},{"id":"2509.17396","title":"EpiCache: Episodic KV Cache Management for Long-Term Conversation on Resource-Constrained Environments","created":"2025-09-22","cited_by_count":7,"area":"inference"},{"id":"2605.05971","title":"Training Transformers for KV Cache Compressibility","created":"2026-05-07","cited_by_count":7,"area":"inference"},{"id":"2607.07847","title":"When Does Continual Learning Require Learning","created":"2026-07-08","cited_by_count":7,"area":"inference"},{"id":"2606.04557","title":"Cartridges at Scale: Training Modular KV Caches over Large Document Collections","created":"2026-06-03","cited_by_count":6,"area":"inference"},{"id":"2602.24287","title":"Do LLMs Benefit From Their Own Words?","created":"2026-02-27","cited_by_count":5,"area":null},{"id":"2603.02540","title":"A Neuropsychologically Grounded Evaluation of LLM Cognitive Abilities","created":"2026-03-03","cited_by_count":5,"area":null},{"id":"2605.23296","title":"Parallel Context Compaction for Long-Horizon LLM Agent Serving","created":"2026-05-22","cited_by_count":5,"area":"agents"},{"id":"2605.05602","title":"Nearly Optimal Attention Coresets","created":"2026-05-07","cited_by_count":4,"area":null},{"id":"2605.15156","title":"MeMo: Memory as a Model","created":"2026-05-14","cited_by_count":4,"area":null},{"id":"2606.07878","title":"Still: Amortized KV Cache Compaction in a Single Forward Pass","created":"2026-06-05","cited_by_count":4,"area":"inference"},{"id":"2606.09659","title":"End-to-End Context Compression at Scale","created":"2026-06-08","cited_by_count":4,"area":"inference"},{"id":"2608.05475","title":"KV-Skill: Forging Expertise in the Model's Native Language","created":"2026-08-05","cited_by_count":4,"area":null},{"id":"2510.20535","title":"ARC-Encoder: learning compressed text representations for large language models","created":"2025-10-23","cited_by_count":3,"area":"lr"},{"id":"2602.02366","title":"ReasonCACHE: Teaching LLMs To Reason Without Weight Updates","created":"2026-02-02","cited_by_count":3,"area":"lr"},{"id":"2605.09778","title":"Nectar: Neural Estimation of Cached-Token Attention via Regression","created":"2026-05-10","cited_by_count":3,"area":null},{"id":"2608.01247","title":"RestoreKV: Recovering Full-Cache Behavior Under Aggressive Query-Agnostic KV Cache Eviction","created":"2026-08-02","cited_by_count":3,"area":"inference"},{"id":"2508.17032","title":"Learned Structure in Cartridges: Keys as Shareable Routers in Self-Studied Representations","created":"2025-08-23","cited_by_count":2,"area":"inference"},{"id":"2511.03092","title":"SnapStream: Efficient Long Sequence Decoding on Dataflow Accelerators","created":"2025-11-05","cited_by_count":2,"area":"inference"},{"id":"2601.21461","title":"L$^3$: Large Lookup Layers","created":"2026-01-29","cited_by_count":2,"area":"moe"},{"id":"2603.15653","title":"Recursive Language Models Meet Uncertainty: The Surprising Effectiveness of Self-Reflective Program Search for Long Context","created":"2026-03-07","cited_by_count":2,"area":null},{"id":"2604.02339","title":"SIEVE: Sample-Efficient Parametric Learning from Natural Language","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2604.18002","title":"Neural Garbage Collection: Learning to Forget while Learning to Reason","created":"2026-04-20","cited_by_count":2,"area":"lr"},{"id":"2604.22294","title":"SLIDERS: Systematic Reviews via Automated Evidence Synthesis and Reconciliation","created":"2026-04-24","cited_by_count":2,"area":null},{"id":"2605.24432","title":"Found in Conversation: LLMs Teach Themselves to Close the Multi-Turn Gap","created":"2026-05-23","cited_by_count":2,"area":null},{"id":"2606.03979","title":"Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories","created":"2026-06-02","cited_by_count":2,"area":null},{"id":"2606.12400","title":"Doc-to-Atom: Learning to Compile and Compose Memory Atoms","created":"2026-06-10","cited_by_count":2,"area":"lr"},{"id":"2608.00902","title":"Practical Online KV Cache Compaction for LLM Agents: An Empirical Study","created":"2026-08-02","cited_by_count":2,"area":"lr"},{"id":"2608.01672","title":"Learning What to Remember: Test-Time Training via Context Distillation","created":"2026-08-03","cited_by_count":2,"area":null},{"id":"2608.26070","title":"Prefix Sliding for efficient test-time scaling","created":"2026-08-26","cited_by_count":2,"area":"lr"},{"id":"2609.35621","title":"Cartridges++: KV Cache Compression without Off-Context Derailment","created":"2026-09-28","cited_by_count":2,"area":"inference"},{"id":"2512.09723","title":"Mixture of Lookup Key-Value Experts","created":"2025-12-10","cited_by_count":1,"area":null},{"id":"2603.23562","title":"Synthetic Mixed Training: Scaling Parametric Knowledge Acquisition Beyond RAG","created":"2026-03-24","cited_by_count":1,"area":null},{"id":"2607.27600","title":"Back from the Future: Key-Value Cache Management by Counter-Causal Surprise","created":"2026-07-30","cited_by_count":1,"area":"inference"},{"id":"2607.28263","title":"CoMem: Reusing Transformer Depth across Queries with Persistent Intermediate Residuals","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2608.00311","title":"SeDeM: Selective Decompression of Hidden-State Memories for Long-Context Question Answering","created":"2026-07-31","cited_by_count":1,"area":null},{"id":"2608.30647","title":"What It Costs to Compose, Rebuild, and Correct Precomputed Memory","created":"2026-08-31","cited_by_count":1,"area":"inference"},{"id":"2609.20820","title":"Workspace Models: Lightweight Robotic Memory via Saliency-Driven Supervision","created":"2026-09-17","cited_by_count":1,"area":null},{"id":"2609.36835","title":"ARC-KV: Amortizing Anchor Search for Reconstruction-Based KV Cache Compaction","created":"2026-09-29","cited_by_count":1,"area":"inference"},{"id":"2609.37988","title":"KV-Kaizen: Learning Context-Adaptive Cache Compression Choices","created":"2026-09-29","cited_by_count":1,"area":"inference"},{"id":"2609.39329","title":"PatchKV: Weight-Space Compensation of KV Cache","created":"2026-09-30","cited_by_count":1,"area":"inference"},{"id":"2609.39358","title":"Working Around the Compute Ceiling: Byte-Exact Memory in Galahad Makes LLM Reading a One-Time Cost LLM Reading a One-Time Cost","created":"2026-09-30","cited_by_count":1,"area":null},{"id":"2512.23049","title":"Accelerating Language Model Workflows with Prompt Choreography","created":"2025-12-28","cited_by_count":0,"area":null},{"id":"2604.11628","title":"Back to Basics: Let Conversational Agents Remember with Just Retrieval and Generation","created":"2026-04-13","cited_by_count":0,"area":"lr"},{"id":"2605.14217","title":"PreFT: Prefill-only finetuning for efficient inference","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2605.15220","title":"Always Learning, Always Mixing: Efficient and Simple Data Mixing All The Time","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.26099","title":"Do Language Models Need Sleep? Offline Recurrence for Improved Online Inference","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2606.29503","title":"The Verbose Context Problem in Medical Records","created":"2026-06-28","cited_by_count":0,"area":null},{"id":"2607.01208","title":"Distill to Detect: Exposing Stealth Biases in LLMs through Cartridge Distillation","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2607.21861","title":"Data Quality over Capacity: Internalizing Documents into LoRA Adapters for Closed-Book QA","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2608.12331","title":"Thought-Aware KV Cache Compaction for Reasoning via Adaptive Attention Matching","created":"2026-06-01","cited_by_count":0,"area":"lr"},{"id":"2608.28293","title":"A Probabilistic Interpretation of KV Cache Eviction","created":"2026-08-28","cited_by_count":0,"area":"inference"},{"id":"2609.17346","title":"Where Should a Document Live: Context, Representations, or Parameters?","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.31415","title":"Evaluating the accuracy of KV cache reuse techniques","created":"2026-09-25","cited_by_count":0,"area":"inference"},{"id":"2609.31640","title":"Measure Learning at Steady State: A BIRD-SQL Formula 1 Case Study","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.33759","title":"Positions Are Not Facts: The Mismatch Between KV Caches and Memory","created":"2026-09-27","cited_by_count":0,"area":"inference"},{"id":"2609.35139","title":"CacheRepair: Learning to Repair Cross-Chunk Context in RAG for KV Cache Fusion","created":"2026-09-28","cited_by_count":0,"area":"rag"},{"id":"2609.37587","title":"ReLMem: Learning Recurrent Memory for Longitudinal EHR Modeling","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.03858","title":"Retrieval-Centric Deep Learning in Growing Nonparametric Neural Networks","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.05885","title":"The Optimization Landscape of Learning Compacted Context Models","created":"2026-10-05","cited_by_count":0,"area":"inference"},{"id":"2610.12133","title":"Rehearse Everything, Remember Nothing: Attic-KV Rehearses What Will Be Read","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.15882","title":"Engram Injection: A Study of Temporal Validity in Parametric Language-Model Memory","created":"2026-10-11","cited_by_count":0,"area":null},{"id":"2610.17355","title":"WIRE: Weight Space Implicit Representation Encoding of Frozen Video LLMs","created":"2026-10-12","cited_by_count":0,"area":"inference"},{"id":"2610.17686","title":"Encoding Context into LLM Weights: What Makes It Context?","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.18654","title":"Kwai Summary Attention V2 Technical Report","created":"2026-10-13","cited_by_count":0,"area":"inference"},{"id":"2610.19210","title":"Titan-Llama: Retrofitting Pre-trained LLMs with External Neural Memory Modules","created":"2026-10-13","cited_by_count":0,"area":"inference"},{"id":"2610.19687","title":"Function-Space Temporal Self-Distillation for Policy Optimization","created":"2026-10-14","cited_by_count":0,"area":"lr"},{"id":"2610.20582","title":"Latent Compaction with Test-Time Training","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}