{"total":57,"rows":[{"id":"2503.16419","title":"Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models","created":"2025-03-20","cited_by_count":464,"area":"lr"},{"id":"2412.19442","title":"A Survey on Large Language Model Acceleration based on KV Cache Management","created":"2024-12-27","cited_by_count":131,"area":"lr"},{"id":"2501.19324","title":"Reward-Guided Speculative Decoding for Efficient LLM Reasoning","created":"2025-01-31","cited_by_count":106,"area":"lr"},{"id":"2410.19258","title":"Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasoning","created":"2024-10-25","cited_by_count":97,"area":"lr"},{"id":"2406.09136","title":"Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs","created":"2024-06-13","cited_by_count":96,"area":"lr"},{"id":"2407.21018","title":"ThinK: Thinner Key Cache by Query-Driven Pruning","created":"2024-07-30","cited_by_count":68,"area":"lr"},{"id":"2412.03213","title":"ClusterKV: Manipulating LLM KV Cache in Semantic Space for Recallable Compression","created":"2024-12-04","cited_by_count":65,"area":"lr"},{"id":"2509.25911","title":"Mem-{\\alpha}: Learning Memory Construction via Reinforcement Learning","created":"2025-09-30","cited_by_count":55,"area":"lr"},{"id":"2503.06692","title":"InftyThink: Breaking the Length Limits of Long-Context Reasoning in Large Language Models","created":"2025-03-09","cited_by_count":54,"area":"lr"},{"id":"2505.24133","title":"R-KV: Redundancy-aware KV Cache Compression for Reasoning Models","created":"2025-05-30","cited_by_count":54,"area":"lr"},{"id":"2606.13392","title":"MiniMax Sparse Attention","created":"2026-06-11","cited_by_count":44,"area":"lr"},{"id":"2410.18517","title":"KVSharer: Efficient Inference via Layer-Wise Dissimilar KV Cache Sharing","created":"2024-10-24","cited_by_count":41,"area":"lr"},{"id":"2506.08889","title":"SeerAttention-R: Sparse Attention Adaptation for Long Reasoning","created":"2025-06-10","cited_by_count":30,"area":"lr"},{"id":"2505.18610","title":"PM-KVQ: Progressive Mixed-precision KV Cache Quantization for Long-CoT LLMs","created":"2025-05-24","cited_by_count":22,"area":"lr"},{"id":"2604.04921","title":"TriAttention: Efficient Long Reasoning with Trigonometric KV Compression","created":"2026-04-06","cited_by_count":21,"area":"lr"},{"id":"2505.13866","title":"Reasoning Path Compression: Compressing Generation Trajectories for Efficient LLM Reasoning","created":"2025-05-20","cited_by_count":17,"area":"lr"},{"id":"2506.15969","title":"LazyEviction: Lagged KV Eviction with Attention Pattern Observation for Efficient Long Reasoning","created":"2025-06-19","cited_by_count":16,"area":"lr"},{"id":"2412.03409","title":"PrefixKV: Adaptive Prefix KV Cache is What Vision Instruction-Following Models Need for Efficient Generation","created":"2024-12-04","cited_by_count":13,"area":"lr"},{"id":"2510.08525","title":"Which Heads Matter for Reasoning? RL-Guided KV Cache Compression","created":"2025-10-09","cited_by_count":10,"area":"lr"},{"id":"2512.01278","title":"Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding","created":"2025-12-01","cited_by_count":10,"area":"lr"},{"id":"2512.16391","title":"Kascade: A Practical Sparse Attention Method for Long-Context LLM Inference","created":"2025-12-18","cited_by_count":10,"area":"lr"},{"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":"2606.03928","title":"Value-Aware Stochastic KV Cache Eviction for Reasoning Models","created":"2026-06-02","cited_by_count":8,"area":"lr"},{"id":"2505.12992","title":"Fractured Chain-of-Thought Reasoning","created":"2025-05-19","cited_by_count":7,"area":"lr"},{"id":"2512.12008","title":"Hold Onto That Thought: Assessing KV Cache Compression On Reasoning","created":"2025-12-12","cited_by_count":6,"area":"lr"},{"id":"2602.01469","title":"P-EAGLE: Parallel-Drafting EAGLE with Scalable Training","created":"2026-02-01","cited_by_count":6,"area":"lr"},{"id":"2512.07993","title":"SkipKV: Selective Skipping of KV Generation and Storage for Efficient Inference with Large Reasoning Models","created":"2025-12-08","cited_by_count":5,"area":"lr"},{"id":"2601.03066","title":"Do LLMs Encode Functional Importance of Reasoning Tokens?","created":"2026-01-06","cited_by_count":5,"area":"lr"},{"id":"2603.06274","title":"Stem: Rethinking Causal Information Flow in Sparse Attention","created":"2026-03-06","cited_by_count":5,"area":"lr"},{"id":"2607.02509","title":"ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning","created":"2026-07-02","cited_by_count":4,"area":"lr"},{"id":"2505.16950","title":"Bottlenecked Transformers: Periodic KV Cache Consolidation for Generalised Reasoning","created":"2025-05-22","cited_by_count":3,"area":"lr"},{"id":"2606.11164","title":"ReasonAlloc: Hierarchical Decoding-Time KV Cache Budget Allocation for Reasoning Models","created":"2026-06-09","cited_by_count":3,"area":"lr"},{"id":"2602.15843","title":"The Perplexity Paradox: Why Code Compresses Better Than Math in LLM Prompts","created":"2026-01-21","cited_by_count":2,"area":"lr"},{"id":"2605.06850","title":"How to Compress KV Cache in RL Post-Training? Shadow Mask Distillation for Memory-Efficient Alignment","created":"2026-05-07","cited_by_count":2,"area":"lr"},{"id":"2606.26472","title":"Epiphany-Aware KV Cache Eviction Without the Attention Matrix","created":"2026-06-25","cited_by_count":2,"area":"lr"},{"id":"2608.15797","title":"KV-Rescue: Recovering Reasoning Language Model KV Eviction Loss via Stepwise Interleaving","created":"2026-08-16","cited_by_count":2,"area":"lr"},{"id":"2608.26070","title":"Prefix Sliding for efficient test-time scaling","created":"2026-08-26","cited_by_count":2,"area":"lr"},{"id":"2602.11530","title":"PASCAL: A Phase-Aware Scheduling Algorithm for Serving Reasoning-based Large Language Models","created":"2026-02-12","cited_by_count":1,"area":"lr"},{"id":"2605.06997","title":"Echo: KV-Cache-Free Associative Recall with Spectral Koopman Operators","created":"2026-05-07","cited_by_count":1,"area":"lr"},{"id":"2605.23200","title":"Adaptive Mass-Segmented KV Compression for Long-Context Reasoning","created":"2026-05-22","cited_by_count":1,"area":"lr"},{"id":"2609.03430","title":"Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning","created":"2026-09-03","cited_by_count":1,"area":"lr"},{"id":"2609.27373","title":"Attention Routing Stabilizes Early: Working-Set Inference for Recurrent Language Models","created":"2026-09-23","cited_by_count":1,"area":"lr"},{"id":"2510.05176","title":"PatternKV: Flattening KV Representation Expands Quantization Headroom","created":"2025-10-05","cited_by_count":0,"area":"lr"},{"id":"2512.20954","title":"Reflection Pretraining Enables Token-Level Self-Correction in Biological Sequence Models","created":"2025-12-24","cited_by_count":0,"area":"lr"},{"id":"2602.00748","title":"HyperOffload: Graph-Driven Hierarchical Memory Management for Large Language Models on SuperNode Architectures","created":"2026-01-31","cited_by_count":0,"area":"lr"},{"id":"2603.27960","title":"Towards Efficient Large Vision-Language Models: A Comprehensive Survey on Inference Strategies","created":"2026-03-30","cited_by_count":0,"area":"lr"},{"id":"2604.10898","title":"ZoomR: Memory Efficient Reasoning through Multi-Granularity Key Value Retrieval","created":"2026-04-13","cited_by_count":0,"area":"lr"},{"id":"2606.03768","title":"HybridThinker: Efficient Chain-of-Thought Reasoning via Compressed Memory and Transient Thought Steps","created":"2026-06-02","cited_by_count":0,"area":"lr"},{"id":"2606.05201","title":"State commitment learning: training language models to distinguish computation from memory","created":"2026-05-22","cited_by_count":0,"area":"lr"},{"id":"2606.24937","title":"The Hitchhiker's Guide to Agentic AI: From Foundations to Systems","created":"2026-06-22","cited_by_count":0,"area":"lr"},{"id":"2607.19358","title":"LISA: Linear-Indexed Sparse Attention for Efficient Long-Context Reasoning","created":"2026-05-29","cited_by_count":0,"area":"lr"},{"id":"2609.03494","title":"GrowPage: On-Demand KV Budgeting for Efficient LLM Reasoning Serving","created":"2026-09-03","cited_by_count":0,"area":"lr"},{"id":"2609.04971","title":"BeaconKV: Key-Value Cache Compression Guided by Beacon Queries for Efficient Large Reasoning Model Inference","created":"2026-09-04","cited_by_count":0,"area":"lr"},{"id":"2609.16055","title":"State of Thought Enables Endogenous Reasoning","created":"2026-09-13","cited_by_count":0,"area":"lr"},{"id":"2609.27276","title":"DRSR: Learning Set-Level Deletion Risk for Efficient Long-Horizon Agents","created":"2026-09-23","cited_by_count":0,"area":"lr"},{"id":"2610.10304","title":"SemanticFold: Latent Sequence Compression SeparatesLanguage Modeling, Decodability, and Reasoning","created":"2026-10-07","cited_by_count":0,"area":"lr"}],"next_cursor":null}