{"total":126,"rows":[{"id":"2507.05257","title":"Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions","created":"2025-07-07","cited_by_count":254,"area":"agents"},{"id":"2601.02780","title":"MiMo-V2-Flash Technical Report","created":"2026-01-06","cited_by_count":191,"area":"moe"},{"id":"2510.05381","title":"Context Length Alone Hurts LLM Performance Despite Perfect Retrieval","created":"2025-10-06","cited_by_count":127,"area":null},{"id":"2503.11951","title":"SagaLLM: Context Management, Validation, and Transaction Guarantees for Multi-Agent LLM Planning","created":"2025-03-15","cited_by_count":60,"area":"agents"},{"id":"2508.21433","title":"The Complexity Trap: Simple Observation Masking Is as Efficient as LLM Summarization for Agent Context Management","created":"2025-08-29","cited_by_count":48,"area":"agents"},{"id":"2511.02817","title":"Oolong: Evaluating Long Context Reasoning and Aggregation Capabilities","created":"2025-11-04","cited_by_count":40,"area":null},{"id":"2505.20096","title":"MA-RAG: Multi-Agent Retrieval-Augmented Generation via Collaborative Chain-of-Thought Reasoning","created":"2025-05-26","cited_by_count":26,"area":"lr"},{"id":"2605.12493","title":"LongMemEval-V2: Evaluating Long-Term Agent Memory Toward Experienced Colleagues","created":"2026-05-12","cited_by_count":23,"area":"agents"},{"id":"2502.20790","title":"Chain-of-Thought Matters: Improving Long-Context Language Models with Reasoning Path Supervision","created":"2025-02-28","cited_by_count":21,"area":"lr"},{"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":"2505.10570","title":"LongFuncEval: Measuring the effectiveness of long context models for function calling","created":"2025-04-30","cited_by_count":18,"area":"agents"},{"id":"2601.21468","title":"MemOCR: Layout-Aware Visual Memory for Efficient Long-Horizon Reasoning","created":"2026-01-29","cited_by_count":15,"area":"agents"},{"id":"2506.21614","title":"LastingBench: Defend Benchmarks Against Knowledge Leakage","created":"2025-06-21","cited_by_count":14,"area":null},{"id":"2510.06557","title":"The Markovian Thinker: Architecture-Agnostic Linear Scaling of Reasoning","created":"2025-10-08","cited_by_count":13,"area":"lr"},{"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":"2512.15649","title":"VTCBench: Can Vision-Language Models Understand Long Context with Vision-Text Compression?","created":"2025-12-17","cited_by_count":11,"area":"mllm"},{"id":"2508.07479","title":"Positional Biases Shift as Inputs Approach Context Window Limits","created":"2025-08-10","cited_by_count":9,"area":null},{"id":"2601.20730","title":"AgentLongBench: A Controllable Long Benchmark For Long-Contexts Agents via Environment Rollouts","created":"2026-01-28","cited_by_count":9,"area":"agents"},{"id":"2603.27490","title":"AgentSwing: Adaptive Parallel Context Management Routing for Long-Horizon Web Agents","created":"2026-03-29","cited_by_count":9,"area":"agents"},{"id":"2608.05179","title":"Autonomous Research Agents: A Survey of AI Scientists and the Verification Gap","created":"2026-06-29","cited_by_count":9,"area":"agents"},{"id":"2508.00554","title":"ContestTrade: A Multi-Agent Trading System Based on Internal Contest Mechanism","created":"2025-08-01","cited_by_count":8,"area":"agents"},{"id":"2601.07226","title":"Lost in the Noise: How Reasoning Models Fail with Contextual Distractors","created":"2026-01-12","cited_by_count":8,"area":"lr"},{"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":"2606.06256","title":"RedKnot: Efficient Long-Context LLM Serving with Head-Aware KV Reuse and SegPagedAttention","created":"2026-06-04","cited_by_count":7,"area":"inference"},{"id":"2605.24002","title":"Harnessing AtomisticSkills for Agentic Atomistic Research","created":"2026-05-18","cited_by_count":6,"area":"agents"},{"id":"2605.28732","title":"MemTrace: Tracing and Attributing Errors in Large Language Model Memory Systems","created":"2026-05-27","cited_by_count":6,"area":"lr"},{"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":"2605.23296","title":"Parallel Context Compaction for Long-Horizon LLM Agent Serving","created":"2026-05-22","cited_by_count":5,"area":"agents"},{"id":"2605.24279","title":"ContextEcho: A Benchmark for Persona Drift in Long Agentic-Coding Sessions","created":"2026-05-22","cited_by_count":5,"area":"agents"},{"id":"2608.31075","title":"Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence","created":"2026-08-31","cited_by_count":5,"area":"lr"},{"id":"2510.22371","title":"Reasoning Models Reason Well, Until They Don't","created":"2025-10-25","cited_by_count":4,"area":"lr"},{"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":"2607.08032","title":"What to Keep, What to Forget: A Rate--Distortion View of Memory Compaction in LLMs and Agents","created":"2026-07-09","cited_by_count":4,"area":"agents"},{"id":"2608.19181","title":"Beyond Teacher Likelihood: Group-Calibrated On-Policy Distillation for Long-Context Reasoning","created":"2026-08-19","cited_by_count":4,"area":"distill"},{"id":"2608.21690","title":"Context as an Environment: Programmatic Context Management for Long-Horizon Agents","created":"2026-08-21","cited_by_count":4,"area":"agents"},{"id":"2505.19091","title":"ReadBench: Measuring the Dense Text Visual Reading Ability of Vision-Language Models","created":"2025-05-25","cited_by_count":3,"area":"mllm"},{"id":"2509.00529","title":"Modeling Motivated Reasoning in Law: Evaluating Strategic Role Conditioning in LLM Summarization","created":"2025-08-30","cited_by_count":3,"area":"lr"},{"id":"2509.18458","title":"CogniLoad: A Synthetic Natural Language Reasoning Benchmark With Tunable Length, Intrinsic Difficulty, and Distractor Density","created":"2025-09-22","cited_by_count":3,"area":"lr"},{"id":"2510.14453","title":"Natural Language Tools: A Natural Language Approach to Tool Calling In Large Language Agents","created":"2025-10-16","cited_by_count":3,"area":"agents"},{"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":"2602.08874","title":"Do Reasoning LLMs Refuse What They Infer in Long Contexts?","created":"2026-02-09","cited_by_count":3,"area":"lr"},{"id":"2606.29718","title":"Diagnosing and Mitigating Context Rot in Long-horizon Search","created":"2026-06-29","cited_by_count":3,"area":null},{"id":"2504.00187","title":"Insight-RAG: Enhancing LLMs with Insight-Driven Augmentation","created":"2025-03-31","cited_by_count":2,"area":"rag"},{"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":"2604.21816","title":"Tool Attention Is All You Need: Dynamic Tool Gating and Lazy Schema Loading for Eliminating the MCP/Tools Tax in Scalable Agentic Workflows","created":"2026-04-23","cited_by_count":2,"area":"agents"},{"id":"2605.05806","title":"Retrieval from Within: An Intrinsic Capability of Attention-Based Models","created":"2026-05-07","cited_by_count":2,"area":"rag"},{"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":"2605.12477","title":"MEME: Multi-entity & Evolving Memory Evaluation","created":"2026-05-12","cited_by_count":2,"area":"agents"},{"id":"2607.22711","title":"CORVUS: Context Optimization and Reduction Via Underlying Synchronization for LLM Coding Agents","created":"2026-07-20","cited_by_count":2,"area":"agents"},{"id":"2607.25398","title":"HANDBOOK.md: A Benchmark for Long-Context Agentic Instruction Following","created":"2026-07-28","cited_by_count":2,"area":"agents"},{"id":"2608.05141","title":"OctoLong: Mid-Training On Cross-Repository Code Contexts Enhances Long-Context Modeling","created":"2026-08-05","cited_by_count":2,"area":"agents"},{"id":"2608.19993","title":"Optimal Skill Selection for LLM Agents with Provable Bicriteria Guarantees","created":"2026-08-20","cited_by_count":2,"area":"agents"},{"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":"2601.06644","title":"Do Language Models Reason Across Languages?","created":"2026-01-10","cited_by_count":1,"area":"lr"},{"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":"2602.08030","title":"Free(): Learning to Forget in Malloc-Only Reasoning Models","created":"2026-02-08","cited_by_count":1,"area":"lr"},{"id":"2602.09616","title":"With Argus Eyes: Assessing Retrieval Gaps via Uncertainty Scoring to Detect and Remedy Retrieval Blind Spots","created":"2026-02-10","cited_by_count":1,"area":"rag"},{"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":"2603.13091","title":"Reasoning over Video: Evaluating How MLLMs Extract, Integrate, and Reconstruct Spatiotemporal Evidence","created":"2026-03-13","cited_by_count":1,"area":"lr"},{"id":"2605.23170","title":"Positional Failures in Long-Context LLMs: A Blind Spot in Reasoning Benchmarks","created":"2026-05-22","cited_by_count":1,"area":"lr"},{"id":"2605.27243","title":"Can Retrieval Heads See Images? Multimodal Retrieval Heads in Long-Context Vision-Language Models","created":"2026-05-26","cited_by_count":1,"area":"mllm"},{"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":"2606.18831","title":"Beyond Reward Engineering: A Data Recipe for Long-Context Reinforcement Learning","created":"2026-06-17","cited_by_count":1,"area":"lr"},{"id":"2609.01660","title":"How Fast Do Agents Rot? An Empirical Study of Long-Horizon Degradation in LLM Agents for Production Decision-Making","created":"2026-08-31","cited_by_count":1,"area":"agents"},{"id":"2609.15982","title":"The Router Within: Eliciting Native Skill Routing from a Frozen LLM","created":"2026-09-14","cited_by_count":1,"area":"agents"},{"id":"2609.26368","title":"HySparse2: Hybrid Sparse Attention with Two-Level KV Sharing","created":"2026-09-22","cited_by_count":1,"area":"inference"},{"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":"2601.02023","title":"Not All Needles Are Found: How Fact Distribution and Don't Make It Up Prompts Shape Retrieval, Reasoning, and Hallucination in Long-Context LLMs","created":"2026-01-05","cited_by_count":0,"area":"lr"},{"id":"2603.07401","title":"VIVECaption: A Split Approach to Caption Quality Improvement","created":"2026-03-08","cited_by_count":0,"area":null},{"id":"2604.09687","title":"Grid2Matrix: Revealing Digital Agnosia in Vision-Language Models","created":"2026-04-06","cited_by_count":0,"area":"lr"},{"id":"2604.25930","title":"Associative-State Universal Transformers: Sparse Retrieval Meets Structured Recurrence","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2605.12535","title":"Ghost in the Context: Policy-Carriage Integrity in LLM Agents","created":"2026-05-02","cited_by_count":0,"area":"agents"},{"id":"2605.27294","title":"Separating Semantic Competition from Context Length in RAG Reading","created":"2026-05-26","cited_by_count":0,"area":"rag"},{"id":"2606.02680","title":"Post-Boundary Bridge: Must Local Attention Go Global Between Global Layers?","created":"2026-06-01","cited_by_count":0,"area":"inference"},{"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":"2606.06840","title":"Characterize Then Distill: Mechanistic Reasoning in Large Output Spaces","created":"2026-06-05","cited_by_count":0,"area":"lr"},{"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":"2606.10921","title":"Trace Only What You Need: Structure-Aware On-Demand Hypergraph Memory for Long-Document Question Answering","created":"2026-06-09","cited_by_count":0,"area":"rag"},{"id":"2606.13020","title":"SciR: A Controllable Benchmark for Scientific Reasoning in LLMs","created":"2026-06-11","cited_by_count":0,"area":"lr"},{"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":"2606.19338","title":"Beyond the Current Observation: Evaluating Multimodal Large Language Models in Controllable Non-Markov Games","created":"2026-06-17","cited_by_count":0,"area":"mllm"},{"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}],"next_cursor":"100"}