{"total":127,"rows":[{"id":"2604.20006","title":"From Recall to Forgetting: Benchmarking Long-Term Memory for Personalized Agents","created":"2026-04-21","cited_by_count":36,"area":"agents"},{"id":"2603.29919","title":"SkillReducer: Optimizing LLM Agent Skills for Token Efficiency","created":"2026-03-31","cited_by_count":33,"area":"agents"},{"id":"2604.02460","title":"Single-Agent LLMs Outperform Multi-Agent Systems on Multi-Hop Reasoning Under Equal Thinking Token Budgets","created":"2026-04-02","cited_by_count":30,"area":"lr"},{"id":"2604.12285","title":"GAM: Hierarchical Graph-based Agentic Memory for LLM Agents","created":"2026-04-14","cited_by_count":19,"area":"agents"},{"id":"2604.14362","title":"APEX-MEM: Agentic Semi-Structured Memory with Temporal Reasoning for Long-Term Conversational AI","created":"2026-04-15","cited_by_count":17,"area":"lr"},{"id":"2606.28434","title":"SWE-MeM: Learning Adaptive Memory Management for Long-Horizon Coding Agents","created":"2026-06-26","cited_by_count":15,"area":"agents"},{"id":"2604.16968","title":"On Safety Risks in Experience-Driven Self-Evolving Agents","created":"2026-04-18","cited_by_count":14,"area":"agents"},{"id":"2605.12357","title":"$\\delta$-mem: Efficient Online Memory for Large Language Models","created":"2026-05-12","cited_by_count":13,"area":null},{"id":"2602.11243","title":"Evaluating Memory Structure in LLM Agents","created":"2026-02-11","cited_by_count":12,"area":"rag"},{"id":"2602.21611","title":"Structurally Aligned Subtask-Level Memory for Software Engineering Agents","created":"2026-02-25","cited_by_count":12,"area":"agents"},{"id":"2603.20432","title":"Coding Agents are Effective Long-Context Processors","created":"2026-03-20","cited_by_count":12,"area":"agents"},{"id":"2605.26548","title":"SEC-bench Pro: Can Language Models Solve Long-Horizon Software Security Tasks?","created":"2026-05-26","cited_by_count":9,"area":null},{"id":"2511.03475","title":"ContextPilot: Fast Long-Context Inference via Context Reuse","created":"2025-11-05","cited_by_count":8,"area":"inference"},{"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":"2605.15514","title":"RoPE Distinguishes Neither Positions Nor Tokens in Long Contexts, Provably","created":"2026-05-15","cited_by_count":8,"area":null},{"id":"2603.21321","title":"Improving Coherence and Persistence in Agentic AI for System Optimization","created":"2026-03-22","cited_by_count":7,"area":"agents"},{"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":"2601.12906","title":"Gated Differentiable Working Memory for Long-Context Language Modeling","created":"2026-01-19","cited_by_count":6,"area":null},{"id":"2602.00185","title":"QUASAR: A Universal Autonomous System for Atomistic Simulation and a Benchmark of Its Capabilities","created":"2026-01-30","cited_by_count":6,"area":"agents"},{"id":"2603.17343","title":"EvoGuard: An Extensible Agentic RL-based Framework for Practical and Evolving AI-Generated Image Detection","created":"2026-03-18","cited_by_count":6,"area":"agents"},{"id":"2605.08580","title":"Slipstream: Trajectory-Grounded Compaction Validation for Long-Horizon Agents","created":"2026-05-09","cited_by_count":6,"area":"agents"},{"id":"2605.23071","title":"The Efficiency Frontier: A Unified Framework for Cost-Performance Optimization in LLM Context Management","created":"2026-05-21","cited_by_count":6,"area":null},{"id":"2604.13346","title":"AgentSPEX: An Agent SPecification and EXecution Language","created":"2026-04-14","cited_by_count":5,"area":"agents"},{"id":"2605.23296","title":"Parallel Context Compaction for Long-Horizon LLM Agent Serving","created":"2026-05-22","cited_by_count":5,"area":"agents"},{"id":"2601.15300","title":"Intelligence Degradation in Long-Context LLMs: Critical Threshold Determination via Natural Length Distribution Analysis","created":"2026-01-07","cited_by_count":4,"area":null},{"id":"2602.08561","title":"Automating Computational Reproducibility in Social Science: Comparing Prompt-Based and Agent-Based Approaches","created":"2026-02-09","cited_by_count":4,"area":"agents"},{"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":"2511.19730","title":"Training-Free Active Learning Framework in Materials Science with Large Language Models","created":"2025-11-24","cited_by_count":3,"area":null},{"id":"2602.05883","title":"A Guide to Large Language Models in Modeling and Simulation: From Core Techniques to Critical Challenges","created":"2026-02-05","cited_by_count":3,"area":null},{"id":"2602.16653","title":"Agent Skill Framework: Perspectives on the Potential of Small to Medium Language Models in Industrial Environments","created":"2026-02-18","cited_by_count":3,"area":"agents"},{"id":"2604.00555","title":"Ontology-Constrained Neural Reasoning in Enterprise Agentic Systems: A Neurosymbolic Architecture for Domain-Grounded AI Agents","created":"2026-04-01","cited_by_count":3,"area":"lr"},{"id":"2604.01161","title":"Reasoning Shift: How Context Silently Shortens LLM Reasoning","created":"2026-04-01","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":"2607.02607","title":"Latent Visual Cache for Video Reasoning","created":"2026-07-01","cited_by_count":3,"area":"mllm"},{"id":"2607.07548","title":"Think Big, Search Small: Where Capacity Matters in Hierarchical Search Agents?","created":"2026-07-08","cited_by_count":3,"area":"lr"},{"id":"2510.27206","title":"Fints: Efficient Inference-Time Personalization for LLMs with Fine-Grained Instance-Tailored Steering","created":"2025-10-31","cited_by_count":2,"area":null},{"id":"2511.19768","title":"Prune-Then-Plan: Step-Level Calibration for Stable Frontier Exploration in Embodied Question Answering","created":"2025-11-24","cited_by_count":2,"area":"mllm"},{"id":"2512.11485","title":"Mistake Notebook Learning: Batch-Clustered Failures for Training-Free Agent Adaptation","created":"2025-12-12","cited_by_count":2,"area":"agents"},{"id":"2603.29678","title":"View-oriented Conversation Compiler for Agent Trace Analysis","created":"2026-03-31","cited_by_count":2,"area":null},{"id":"2604.10044","title":"LoopGuard: Breaking Self-Reinforcing Attention Loops via Dynamic KV Cache Intervention","created":"2026-04-11","cited_by_count":2,"area":"inference"},{"id":"2605.07076","title":"Self-Consolidating Language Models: Continual Knowledge Incorporation from Context","created":"2026-05-08","cited_by_count":2,"area":null},{"id":"2605.08212","title":"LLMs with in-context learning for Algorithmic Theoretical Physics","created":"2026-05-06","cited_by_count":2,"area":null},{"id":"2606.25191","title":"To Isolate or to Score? Model-Adaptive Assessment for Cost-Efficient Multi-Agent RAG","created":"2026-06-23","cited_by_count":2,"area":"rag"},{"id":"2607.10856","title":"How Do Practitioners Build SE Agents? Insights from a Mixed-Methods Study","created":"2026-07-12","cited_by_count":2,"area":"agents"},{"id":"2607.12963","title":"The Illusion of Robustness: Aggregate Accuracy Hides Prediction Flips under Task-Irrelevant Context","created":"2026-07-14","cited_by_count":2,"area":null},{"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":"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":"2601.05582","title":"Can large language models interpret unstructured chat data on dynamic group decision-making processes? Evidence on joint destination choice","created":"2026-01-09","cited_by_count":1,"area":null},{"id":"2601.20831","title":"MemCtrl: Using MLLMs as Active Memory Controllers on Embodied Agents","created":"2026-01-28","cited_by_count":1,"area":"agents"},{"id":"2602.00851","title":"Persuasion Propagation: Does Persuasion Change AI Agent Behavior?","created":"2026-01-31","cited_by_count":1,"area":null},{"id":"2603.06870","title":"LEAD: Breaking the No-Recovery Bottleneck in Long-Horizon Reasoning","created":"2026-03-06","cited_by_count":1,"area":"lr"},{"id":"2603.08819","title":"Beyond Relevance: On the Relationship Between Retrieval and RAG Information Coverage","created":"2026-03-09","cited_by_count":1,"area":"rag"},{"id":"2603.26728","title":"SEAR: Schema-Based Evaluation and Routing for LLM Gateways","created":"2026-03-20","cited_by_count":1,"area":null},{"id":"2605.18327","title":"Causely: A Causal Intelligence Layer for Enterprise AI A Benchmark Study on SRE and Reliability Workflows","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2605.27706","title":"Chain-based Adaptive Reconfiguration Over Lattices for Hallucination Reduction","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2605.29522","title":"DeepSurvey: Agent-Oriented Automated Survey Generation with Analytical Depth and Citation Reliability","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2606.13733","title":"How Task Structure Limits Multi-Agent Success: An Information-Theoretic Analysis","created":"2026-06-11","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":"2607.01061","title":"Agentic generation of verifiable rules for deterministic, self-expanding reaction classification","created":"2026-07-01","cited_by_count":1,"area":"agents"},{"id":"2608.01742","title":"MemSIF: From Structured Interactions to Dual-Track Fact Memory for LLM Agents","created":"2026-08-03","cited_by_count":1,"area":"agents"},{"id":"2608.21252","title":"EnSI-RAG: Entity-Structure-Indexed Retrieval-Augmented Generation for Long-Document Question Answering","created":"2026-08-21","cited_by_count":1,"area":"rag"},{"id":"2608.25217","title":"LLM-Driven, Datasheet-Aware Automated Hardware Compatibility Verification for Early-Stage, Pre-Schematic Embedded System Design","created":"2026-08-25","cited_by_count":1,"area":null},{"id":"2609.32809","title":"Overwhelmed by Choice: Studying LLM Decision Making at Scale","created":"2026-09-26","cited_by_count":1,"area":"lr"},{"id":"2512.05576","title":"CureAgent: A Training-Free Executor-Analyst Framework for Clinical Reasoning","created":"2025-12-05","cited_by_count":0,"area":"lr"},{"id":"2512.06048","title":"The Road of Adaptive AI for Precision in Cybersecurity","created":"2025-12-05","cited_by_count":0,"area":null},{"id":"2601.14429","title":"Measuring the State of Open Science in Transportation Using Large Language Models","created":"2026-01-20","cited_by_count":0,"area":null},{"id":"2602.08237","title":"Document Reconstruction Unlocks Scalable Long-Context RLVR","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2602.15859","title":"From Transcripts to AI Agents: Knowledge Extraction, RAG Integration, and Robust Evaluation of Conversational AI Assistants","created":"2026-01-26","cited_by_count":0,"area":"agents"},{"id":"2603.15723","title":"Context-Length Robustness in Question Answering Models: A Comparative Empirical Study","created":"2026-03-16","cited_by_count":0,"area":null},{"id":"2603.18334","title":"Can LLMs Reason Like Automated Theorem Provers for Rust Verification? VCoT-Bench: Evaluating via Verification Chain of Thought","created":"2026-03-18","cited_by_count":0,"area":"lr"},{"id":"2603.19008","title":"Hypothesis-Conditioned Query Rewriting for Decision-Useful Retrieval","created":"2026-03-19","cited_by_count":0,"area":"rag"},{"id":"2603.19250","title":"Can Structural Cues Save LLMs? Evaluating Language Models in Massive Document Streams","created":"2026-02-25","cited_by_count":0,"area":null},{"id":"2603.21278","title":"Conversation Tree Architecture: A Structured Framework for Context-Aware Multi-Branch LLM Conversations","created":"2026-03-22","cited_by_count":0,"area":null},{"id":"2603.29023","title":"Human-Like Lifelong Memory: A Neuroscience-Grounded Architecture for Infinite Interaction","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2604.04599","title":"LP-GEMM: Integrating Layout Propagation into GEMM Operations","created":"2026-04-06","cited_by_count":0,"area":null},{"id":"2604.06416","title":"Attention Flows: Tracing LLM Conceptual Engagement via Story Summaries","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2604.14422","title":"Demonstration of Pneuma-Seeker: Agentic System for Reifying and Fulfilling Information Needs on Tabular Data","created":"2026-04-15","cited_by_count":0,"area":"agents"},{"id":"2604.16913","title":"The Cognitive Penalty: Ablating System 1 and System 2 Reasoning in Edge-Native SLMs for Decentralized Consensus","created":"2026-04-18","cited_by_count":0,"area":"lr"},{"id":"2604.21068","title":"Expanding the extreme-k dielectric materials space through physics-validated generative reasoning","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2605.12694","title":"Agentic Interpretation: Lattice-Structured Evidence for LLM-Based Program Analysis","created":"2026-05-12","cited_by_count":0,"area":"agents"},{"id":"2605.16712","title":"Recall Isn't Enough: Bounding Commitments in Personalized Language Systems","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2605.28714","title":"IPO-Mine: A Toolkit and Dataset for Section-Structured Analysis of Long, Multimodal IPO Documents","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2606.04628","title":"RAMPART: Registry-based Agentic Memory with Priority-Aware Runtime Transformation","created":"2026-06-03","cited_by_count":0,"area":"agents"},{"id":"2606.05275","title":"Personal AI Agent for Camera Roll VQA","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.07995","title":"Customer-Agent: Overcoming Context Limitations in Ultra-Long Shopping Trajectories via Tool-Augmented Agents and RLVR","created":"2026-06-06","cited_by_count":0,"area":"agents"},{"id":"2606.20900","title":"Storyline Trees: Hierarchical Representations for Long-Form Narratives","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2606.25343","title":"Invoice Haystack: Benchmarking Document Retrieval and Visual Question Answering Under Strong Visual Homogeneity","created":"2026-06-24","cited_by_count":0,"area":"mllm"},{"id":"2606.29750","title":"Managing Map Cardinality in Automatic Disease Classification Mapping: Balancing Precision, Recall and Coverage","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2607.12216","title":"RCWT: Measuring Task-Budget Displacement from Coordination Content in LLM Calls","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2607.13921","title":"Generative Compilation: On-the-Fly Compiler Feedback as AI Generates Code","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2607.14386","title":"CIPHER: A Decoupled Exploration-Selection Framework for Test-Time Scaling of Data Science Agents","created":"2026-07-15","cited_by_count":0,"area":"lr"},{"id":"2607.18438","title":"Relay-Bench: Evaluating LLMs on Multi-Domain Reasoning Chains","created":"2026-07-20","cited_by_count":0,"area":"lr"},{"id":"2607.25266","title":"FORGE: Frame Orthogonality in Relevance Geometry for Long-Form Video Understanding","created":"2026-07-28","cited_by_count":0,"area":"mllm"},{"id":"2607.26071","title":"GuidedRAG: Semantic Steering of Retrieval-Augmented Generation","created":"2026-07-10","cited_by_count":0,"area":"rag"},{"id":"2607.29503","title":"The Grokked Illusion: True Equilibrium Mitigates Catastrophic Forgetting","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2608.03048","title":"PI-Mem: Pushing Long-Context Reasoning to 3.6M Tokens with Parallel-Iterative Memory","created":"2026-08-04","cited_by_count":0,"area":"lr"},{"id":"2608.08146","title":"Long SKILL Compliance as Logical Reasoning: Closure-Grounded Detection with Scaling-Guided On-Policy Distillation","created":"2026-08-08","cited_by_count":0,"area":"lr"},{"id":"2608.14838","title":"The Recall Trap: A Recall-Maximizing Retriever Configuration Reduces Issue Resolution in Fixed-Budget Code Context","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2608.19025","title":"Self-prompting and cross-model consensus enable reproducible data extraction from scientific literature with large language models","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2608.22137","title":"MegaMem: A Retrieval Solution for Ultra-Large Context Windows","created":"2026-08-22","cited_by_count":0,"area":null}],"next_cursor":"100"}