{"total":58,"rows":[{"id":"2510.05381","title":"Context Length Alone Hurts LLM Performance Despite Perfect Retrieval","created":"2025-10-06","cited_by_count":127,"area":null},{"id":"2511.02817","title":"Oolong: Evaluating Long Context Reasoning and Aggregation Capabilities","created":"2025-11-04","cited_by_count":40,"area":null},{"id":"2603.01966","title":"AMemGym: Interactive Memory Benchmarking for Assistants in Long-Horizon Conversations","created":"2026-03-02","cited_by_count":20,"area":null},{"id":"2506.21614","title":"LastingBench: Defend Benchmarks Against Knowledge Leakage","created":"2025-06-21","cited_by_count":14,"area":null},{"id":"2510.09869","title":"NarraBench: A Comprehensive Framework for Narrative Benchmarking","created":"2025-10-10","cited_by_count":13,"area":null},{"id":"2507.23701","title":"TextQuests: How Good are LLMs at Text-Based Video Games?","created":"2025-07-31","cited_by_count":12,"area":null},{"id":"2509.21361","title":"Context Is What You Need: The Maximum Effective Context Window for Real World Limits of LLMs","created":"2025-09-21","cited_by_count":12,"area":null},{"id":"2512.12775","title":"Persistent Personas? Role-Playing, Instruction Following, and Safety in Extended Interactions","created":"2025-12-14","cited_by_count":12,"area":null},{"id":"2508.07479","title":"Positional Biases Shift as Inputs Approach Context Window Limits","created":"2025-08-10","cited_by_count":9,"area":null},{"id":"2505.18148","title":"Hidden in the Haystack: Smaller Needles are More Difficult for LLMs to Find","created":"2025-05-23","cited_by_count":7,"area":null},{"id":"2506.02921","title":"A Controllable Examination for Long-Context Language Models","created":"2025-06-03","cited_by_count":7,"area":null},{"id":"2602.11761","title":"MiniCPM-SALA: Hybridizing Sparse and Linear Attention for Efficient Long-Context Modeling","created":"2026-02-12","cited_by_count":5,"area":null},{"id":"2601.03543","title":"EvolMem: A Cognitive-Driven Benchmark for Multi-Session Dialogue Memory","created":"2026-01-07","cited_by_count":4,"area":null},{"id":"2605.10544","title":"Where Does Long-Context Supervision Actually Go? Effective-Context Exposure Balancing","created":"2026-05-11","cited_by_count":4,"area":null},{"id":"2511.13274","title":"KForge: Program Synthesis for Diverse AI Hardware Accelerators","created":"2025-11-17","cited_by_count":3,"area":null},{"id":"2511.19730","title":"Training-Free Active Learning Framework in Materials Science with Large Language Models","created":"2025-11-24","cited_by_count":3,"area":null},{"id":"2601.04350","title":"RIGOURATE: Quantifying Scientific Exaggeration with Evidence-Aligned Claim Evaluation","created":"2026-01-07","cited_by_count":3,"area":null},{"id":"2606.29718","title":"Diagnosing and Mitigating Context Rot in Long-horizon Search","created":"2026-06-29","cited_by_count":3,"area":null},{"id":"2505.13353","title":"Sense and Sensitivity: Examining the Influence of Semantic Recall on Long Context Code Understanding","created":"2025-05-19","cited_by_count":2,"area":null},{"id":"2509.17192","title":"Shall We Play a Game? Language Models for Open-ended Wargames","created":"2025-09-21","cited_by_count":2,"area":null},{"id":"2601.16934","title":"Information Representation Fairness in Long-Document Embeddings: The Peculiar Interaction of Positional and Language Bias","created":"2026-01-23","cited_by_count":2,"area":null},{"id":"2605.06142","title":"IRC-Bench: Recognizing Entities from Contextual Cues in First-Person Reminiscences","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2505.11557","title":"AC-LoRA: (Almost) Training-Free Access Control-Aware Multi-Modal LLMs","created":"2025-05-15","cited_by_count":1,"area":null},{"id":"2506.12189","title":"Supernova Event Dataset: Interpreting Large Language Models' Personality through Critical Event Analysis","created":"2025-06-13","cited_by_count":1,"area":null},{"id":"2506.14407","title":"ImpliRet: Benchmarking the Implicit Fact Retrieval Challenge","created":"2025-06-17","cited_by_count":1,"area":null},{"id":"2509.07309","title":"PIE: Performance Interval Estimation for Free-Form Generation Tasks","created":"2025-09-09","cited_by_count":1,"area":null},{"id":"2510.22956","title":"Tagging-Augmented Generation: Assisting Language Models in Finding Intricate Knowledge In Long Contexts","created":"2025-10-27","cited_by_count":1,"area":null},{"id":"2601.12555","title":"Evaluating Contextually Mediated Factual Recall in Multilingual Large Language Models","created":"2026-01-18","cited_by_count":1,"area":null},{"id":"2603.00270","title":"LLMs Remember First, Forget Last: Dual-Process Interference in Large Language Models","created":"2026-02-27","cited_by_count":1,"area":null},{"id":"2606.04660","title":"LifeSide: Benchmarking Agents as Lifelong Digital Companions","created":"2026-06-03","cited_by_count":1,"area":null},{"id":"2606.09525","title":"Emergence of Context Characteristics Sensitivity in Large Language Models","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2507.02917","title":"Echo State Transformer: Attention Over Finite Memories","created":"2025-06-25","cited_by_count":0,"area":null},{"id":"2510.18691","title":"Investigating LLM Capabilities on Long Context Comprehension for Medical Question Answering","created":"2025-10-21","cited_by_count":0,"area":null},{"id":"2603.07401","title":"VIVECaption: A Split Approach to Caption Quality Improvement","created":"2026-03-08","cited_by_count":0,"area":null},{"id":"2604.25930","title":"Associative-State Universal Transformers: Sparse Retrieval Meets Structured Recurrence","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2606.02963","title":"KForge: LLM-Driven Cross-Platform Kernel Generation for AI Accelerators","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.06203","title":"Dense Contexts Are Hard Contexts: Lexical Density Limits Effective Context in LLMs","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2606.06906","title":"EASE-TTT: Evidence-Aligned Selective Test-Time Training for Long-Context Question Answering","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2606.15641","title":"Distilling Examples into Task Instructions: Enhanced In-Context Learning for Real-World B2B Conversations","created":"2026-06-14","cited_by_count":0,"area":null},{"id":"2606.20900","title":"Storyline Trees: Hierarchical Representations for Long-Form Narratives","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2607.01002","title":"Logit-Contribution Scoring Identifies Non-Literal Retrieval Heads","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2607.08284","title":"Understanding Axes of Difficulty For Long Context Tasks Via PredicateLongBench","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2607.09328","title":"WildTrace: Benchmarking Natural Evidence Trails in Long-Context Reasoning","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2607.16254","title":"More Than Memory: Task-Conditioned Signed FFN Writes in Long-Context Retrieval","created":"2026-06-27","cited_by_count":0,"area":null},{"id":"2607.20484","title":"The Devil is in the Spectrum: Mitigating Representation Collapse in LLMs via Topologically Regularized Side-Path","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2607.20764","title":"ArbiGraph: Arbitrarily Scalable Verifiable Task Graphs for Evaluating Context Management","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2608.06422","title":"Sharding Prevents LLM Oversight Failures and Adversarial Exploitation","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.18988","title":"DeepWeaver: Bridging the Evidence Synthesis Gap in Open-Ended Question Answering","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2608.23265","title":"EvoWiki: Incremental State Overwriting and Traceable Question Answering for Cross-Meeting Knowledge Evolution","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.01320","title":"Automated Event Log Generation from Unstructured Text Using Finetuned LLMs","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.12686","title":"Residual Vector-based Reconstruction as Long-Context Recall Regardless of Context Window Size","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.16189","title":"Position: AI Is Not Ready for Strategic Conflicts","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2609.19113","title":"Playing log(N)-Questions over Wikipedia Abstracts: How Per-Round Errors Compound Under Information Asymmetry","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.21844","title":"Reusing Latent Speech Representations for Query-Conditioned Topic Localization in Transcripts","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.27590","title":"MWE-ECL: Recoverable Long-Range Context Does Not Always Override Local Lexical Priors","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.27925","title":"Learning When Not to Listen: Selective Anti-Interference Pretraining for Language Models","created":"2026-08-22","cited_by_count":0,"area":null},{"id":"2610.01461","title":"NextMe-800: Anticipating Personal Behavior from Months of Egocentric Video","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.18126","title":"Fresh at Decision, Stale at Action: Routing New Information to LLM Decisions Already Made","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}