{"total":103,"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":"2406.02818","title":"Chain of Agents: Large Language Models Collaborating on Long-Context Tasks","created":"2024-06-04","cited_by_count":206,"area":"agents"},{"id":"2402.04617","title":"InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory","created":"2024-02-07","cited_by_count":197,"area":"agents"},{"id":"2502.02533","title":"Multi-Agent Design: Optimizing Agents with Better Prompts and Topologies","created":"2025-02-04","cited_by_count":113,"area":"agents"},{"id":"2401.04259","title":"MARG: Multi-Agent Review Generation for Scientific Papers","created":"2024-01-08","cited_by_count":104,"area":"agents"},{"id":"2506.21605","title":"MemBench: Towards More Comprehensive Evaluation on the Memory of LLM-based Agents","created":"2025-06-20","cited_by_count":84,"area":"agents"},{"id":"2602.16313","title":"MemoryArena: Benchmarking Agent Memory in Interdependent Multi-Session Agentic Tasks","created":"2026-02-18","cited_by_count":84,"area":"agents"},{"id":"2605.26494","title":"The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence","created":"2026-05-26","cited_by_count":61,"area":"agents"},{"id":"2410.12189","title":"DocETL: Agentic Query Rewriting and Evaluation for Complex Document Processing","created":"2024-10-16","cited_by_count":52,"area":"agents"},{"id":"2506.01300","title":"ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understanding","created":"2025-06-02","cited_by_count":50,"area":"agents"},{"id":"2405.11804","title":"(Perhaps) Beyond Human Translation: Harnessing Multi-Agent Collaboration for Translating Ultra-Long Literary Texts","created":"2024-05-20","cited_by_count":49,"area":"agents"},{"id":"2406.14550","title":"GraphReader: Building Graph-based Agent to Enhance Long-Context Abilities of Large Language Models","created":"2024-06-20","cited_by_count":43,"area":"agents"},{"id":"2412.15266","title":"On the Structural Memory of LLM Agents","created":"2024-12-17","cited_by_count":37,"area":"agents"},{"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":"2602.05665","title":"Graph-based Agent Memory: Taxonomy, Techniques, and Applications","created":"2026-02-05","cited_by_count":25,"area":"agents"},{"id":"2503.06047","title":"DSGBench: A Diverse Strategic Game Benchmark for Evaluating LLM-based Agents in Complex Decision-Making Environments","created":"2025-03-08","cited_by_count":23,"area":"agents"},{"id":"2502.17421","title":"LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification","created":"2025-02-24","cited_by_count":21,"area":"agents"},{"id":"2605.06716","title":"From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms","created":"2026-05-07","cited_by_count":21,"area":"agents"},{"id":"2603.01045","title":"Silo-Bench: A Scalable Environment for Evaluating Distributed Coordination in Multi-Agent LLM Systems","created":"2026-03-01","cited_by_count":20,"area":"agents"},{"id":"2506.13977","title":"CRITICTOOL: Evaluating Self-Critique Capabilities of Large Language Models in Tool-Calling Error Scenarios","created":"2025-06-11","cited_by_count":19,"area":"agents"},{"id":"2505.19433","title":"Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compression","created":"2025-05-26","cited_by_count":16,"area":"agents"},{"id":"2511.13998","title":"LoCoBench-Agent: An Interactive Benchmark for LLM Agents in Long-Context Software Engineering","created":"2025-11-17","cited_by_count":16,"area":"agents"},{"id":"2512.02445","title":"When Refusals Fail: Unstable Safety Mechanisms in Long-Context LLM Agents","created":"2025-12-02","cited_by_count":15,"area":"agents"},{"id":"2603.04814","title":"Beyond the Context Window: A Cost-Performance Analysis of Fact-Based Memory vs. Long-Context LLMs for Persistent Agents","created":"2026-03-05","cited_by_count":15,"area":"agents"},{"id":"2604.04202","title":"ClawArena: Benchmarking AI Agents in Evolving Information Environments","created":"2026-04-05","cited_by_count":11,"area":"agents"},{"id":"2607.05202","title":"EvoAgentBench: Benchmarking Agent Self-Evolution via Ability Transfer","created":"2026-07-06","cited_by_count":11,"area":"agents"},{"id":"2410.20666","title":"Guide-LLM: An Embodied LLM Agent and Text-Based Topological Map for Robotic Guidance of People with Visual Impairments","created":"2024-10-28","cited_by_count":10,"area":"agents"},{"id":"2510.07733","title":"SurveyG: A Multi-Agent LLM Framework with Hierarchical Citation Graph for Automated Survey Generation","created":"2025-10-09","cited_by_count":10,"area":"agents"},{"id":"2607.23809","title":"ACM: Agentic Context Management for Long Horizon Tasks","created":"2026-07-26","cited_by_count":10,"area":"agents"},{"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":"2602.08316","title":"SWE Context Bench: A Benchmark for Context Learning in Coding","created":"2026-02-09","cited_by_count":9,"area":"agents"},{"id":"2506.07675","title":"QUITE: A Query Rewrite System Beyond Rules with LLM Agents","created":"2025-06-09","cited_by_count":8,"area":"agents"},{"id":"2603.05484","title":"Towards Multimodal Lifelong Understanding: A Dataset and Agentic Baseline","created":"2026-03-05","cited_by_count":8,"area":"agents"},{"id":"2606.22528","title":"Governance Decay: How Context Compaction Silently Erases Safety Constraints in Long-Horizon LLM Agents","created":"2026-06-21","cited_by_count":8,"area":"agents"},{"id":"2505.20625","title":"Long Context Scaling: Divide and Conquer via Multi-Agent Question-driven Collaboration","created":"2025-05-27","cited_by_count":7,"area":"agents"},{"id":"2604.26622","title":"OCR-Memory: Optical Context Retrieval for Long-Horizon Agent Memory","created":"2026-04-29","cited_by_count":7,"area":"agents"},{"id":"2607.12893","title":"MemOps: Benchmarking Lifecycle Memory Operations in Long-Horizon Conversations","created":"2026-07-14","cited_by_count":7,"area":"agents"},{"id":"2605.12571","title":"VideoSEAL: Mitigating Evidence Misalignment in Agentic Long Video Understanding by Decoupling Answer Authority","created":"2026-05-12","cited_by_count":6,"area":"agents"},{"id":"2605.17641","title":"Causal Intervention-Based Memory Selection for Long-Horizon LLM Agents","created":"2026-05-17","cited_by_count":6,"area":"agents"},{"id":"2606.18543","title":"CEO-Bench: Can Agents Play the Long Game?","created":"2026-06-16","cited_by_count":6,"area":"agents"},{"id":"2505.23662","title":"ToolHaystack: Stress-Testing Tool-Augmented Language Models in Realistic Long-Term Interactions","created":"2025-05-29","cited_by_count":5,"area":"agents"},{"id":"2605.20833","title":"MemGym: a Long-Horizon Memory Environment for LLM Agents","created":"2026-05-20","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":"2505.21471","title":"Scaling External Knowledge Input Beyond Context Windows of LLMs via Multi-Agent Collaboration","created":"2025-05-27","cited_by_count":4,"area":"agents"},{"id":"2510.07414","title":"Haystack Engineering: Context Engineering for Heterogeneous and Agentic Long-Context Evaluation","created":"2025-10-08","cited_by_count":4,"area":"agents"},{"id":"2602.16493","title":"MMA: Multimodal Memory Agent","created":"2026-02-18","cited_by_count":4,"area":"agents"},{"id":"2603.08727","title":"ARKV: Adaptive and Resource-Efficient KV Cache Management under Limited Memory Budget for Long-Context Inference in LLMs","created":"2026-02-19","cited_by_count":4,"area":"agents"},{"id":"2606.17328","title":"MemTrace: Probing What Final Accuracy Misses in Long-Term Memory","created":"2026-06-15","cited_by_count":4,"area":"agents"},{"id":"2607.01935","title":"A-TMA: Decoupling State-Aware Memory Failures in Long-Term Agent Memory","created":"2026-07-02","cited_by_count":4,"area":"agents"},{"id":"2605.03312","title":"MemFlow: Intent-Driven Memory Orchestration for Small Language Model Agents","created":"2026-05-05","cited_by_count":3,"area":"agents"},{"id":"2606.04555","title":"Temporal Order Matters for Agentic Memory: Segment Trees for Long-Horizon Agents","created":"2026-06-03","cited_by_count":3,"area":"agents"},{"id":"2608.11676","title":"XBridge: Entity-Grounded Latent Bridge for Heterogeneous LLM Communication","created":"2026-08-12","cited_by_count":3,"area":"agents"},{"id":"2608.13334","title":"RippleMem: From Isolated Retrieval to Associative Recollection for Long-Term Agent Memory","created":"2026-08-13","cited_by_count":3,"area":"agents"},{"id":"2511.12676","title":"BridgeEQA: Virtual Embodied Agents for Real Bridge Inspections","created":"2025-11-16","cited_by_count":2,"area":"agents"},{"id":"2601.09382","title":"Long-term Task-oriented Agent: Proactive Long-term Intent Maintenance in Dynamic Environments","created":"2026-01-14","cited_by_count":2,"area":"agents"},{"id":"2603.02631","title":"Cross-Family Speculative Prefill: Training-Free Long-Context Compression with Small Draft Models","created":"2026-03-03","cited_by_count":2,"area":"agents"},{"id":"2603.23840","title":"VehicleMemBench: An Executable Benchmark for Multi-User Long-Term Memory in In-Vehicle Agents","created":"2026-03-25","cited_by_count":2,"area":"agents"},{"id":"2605.02463","title":"When Stress Becomes Signal: Detecting Antifragility-Compatible Regimes in Multi-Agent LLM Systems","created":"2026-05-04","cited_by_count":2,"area":"agents"},{"id":"2605.19099","title":"DecisionBench: A Benchmark for Emergent Delegation in Long-Horizon Agentic Workflows","created":"2026-05-18","cited_by_count":2,"area":"agents"},{"id":"2606.31564","title":"ACE: Pluggable Adaptive Context Elasticizer across Agents","created":"2026-06-30","cited_by_count":2,"area":"agents"},{"id":"2607.12161","title":"Token Reduction Is Not Cost Reduction","created":"2026-07-13","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":"2504.05607","title":"FactGuard: Leveraging Multi-Agent Systems to Generate Answerable and Unanswerable Questions for Enhanced Long-Context LLM Extraction","created":"2025-04-08","cited_by_count":1,"area":"agents"},{"id":"2509.21848","title":"Graph of Agents: Principled Long Context Modeling by Emergent Multi-Agent Collaboration","created":"2025-09-26","cited_by_count":1,"area":"agents"},{"id":"2601.11913","title":"LSTM-MAS: A Long Short-Term Memory Inspired Multi-Agent System for Long-Context Understanding","created":"2026-01-17","cited_by_count":1,"area":"agents"},{"id":"2601.17344","title":"The Shadow Self: Intrinsic Value Misalignment in Large Language Model Agents","created":"2026-01-24","cited_by_count":1,"area":"agents"},{"id":"2603.14597","title":"D-MEM: Dopamine-Gated Agentic Memory via Reward Prediction Error Routing","created":"2026-03-15","cited_by_count":1,"area":"agents"},{"id":"2603.14997","title":"OrgForge: A Multi-Agent Simulation Framework for Verifiable Synthetic Corporate Corpora","created":"2026-03-16","cited_by_count":1,"area":"agents"},{"id":"2605.08503","title":"NARRA-Gym for Evaluating Interactive Narrative Agents","created":"2026-05-08","cited_by_count":1,"area":"agents"},{"id":"2606.08151","title":"Decision-Aware Memory Cards: Counterfactual-Inspired Context Selection and Compression for Tool-Using LLM Agents","created":"2026-06-06","cited_by_count":1,"area":"agents"},{"id":"2606.23961","title":"Forget Without Compromise: Nexus Sampling for Streaming KV-Cache Eviction Under Fixed Budgets","created":"2026-06-22","cited_by_count":1,"area":"agents"},{"id":"2607.09794","title":"Agentic Context Learning with Self-Discovered Specification","created":"2026-07-09","cited_by_count":1,"area":"agents"},{"id":"2607.24762","title":"Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels","created":"2026-06-02","cited_by_count":1,"area":"agents"},{"id":"2608.07915","title":"SPECTRA: Pushing the KV Cache Beyond the 2-Bit Cliff via Spectral Transform Coding","created":"2026-08-08","cited_by_count":1,"area":"agents"},{"id":"2608.22752","title":"The Compaction Cliff in Long-Running AI Agent Memory","created":"2026-08-24","cited_by_count":1,"area":"agents"},{"id":"2608.24252","title":"SA-Bench: Evaluating Semantic Alignment in LLM-Based Paper Reproduction","created":"2026-08-25","cited_by_count":1,"area":"agents"},{"id":"2608.26004","title":"AsymSpec: Context-Asymmetric Speculative Decoding for Agentic LLMs","created":"2026-08-26","cited_by_count":1,"area":"agents"},{"id":"2609.22200","title":"PII-TRACE: A Benchmark for Context-Aware PII Detection in Multi-Turn LLM Conversations","created":"2026-08-31","cited_by_count":1,"area":"agents"},{"id":"2609.27298","title":"StateComp: Learning When to Compress History in Long Horizon Agents","created":"2026-09-23","cited_by_count":1,"area":"agents"},{"id":"2601.20276","title":"Beyond the Needle's Illusion: Decoupled Evaluation of Evidence Access and Use under Semantic Interference at 326M-Token Scale","created":"2026-01-28","cited_by_count":0,"area":"agents"},{"id":"2604.12301","title":"Local-Splitter: A Measurement Study of Seven Tactics for Reducing Cloud LLM Token Usage on Coding-Agent Workloads","created":"2026-04-14","cited_by_count":0,"area":"agents"},{"id":"2604.16736","title":"When Agents Go Quiet: Output Generation Capacity and Format-Cost Separation for LLM Document Synthesis","created":"2026-04-17","cited_by_count":0,"area":"agents"},{"id":"2605.10268","title":"MemReread: Enhancing Agentic Long-Context Reasoning via Memory-Guided Rereading","created":"2026-05-11","cited_by_count":0,"area":"agents"},{"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":"2605.15237","title":"A3D: Agentic AI flow for autonomous Accelerator Design","created":"2026-05-14","cited_by_count":0,"area":"agents"},{"id":"2605.16598","title":"GRASP: Graph Agentic Search over Propositions for Multi-hop Question Answering","created":"2026-05-15","cited_by_count":0,"area":"agents"},{"id":"2606.17041","title":"MetaSyn: A Benchmark for LLM Agents on Meta-Analysis Articles from Nature Portfolio","created":"2026-06-15","cited_by_count":0,"area":"agents"},{"id":"2606.30986","title":"The Organizational Behavior of Agentic AI: Collective Intelligence in Human-Agent Workflows","created":"2026-06-29","cited_by_count":0,"area":"agents"},{"id":"2607.17937","title":"When and How Context Rot Appears in Coding Agents: A White-Box Study of Agent Skills in Code Auditing","created":"2026-07-20","cited_by_count":0,"area":"agents"},{"id":"2608.00009","title":"AgentMemBench: A Systematic Benchmark for Evaluating Long-Term Memory Management Strategies in Conversational AI Agents","created":"2026-06-16","cited_by_count":0,"area":"agents"},{"id":"2608.30181","title":"A.X K2 Technical Report","created":"2026-08-31","cited_by_count":0,"area":"agents"},{"id":"2609.13149","title":"BudgetBench: A Budget-Tiered Protocol and Pilot Harness for Memory Strategy Evaluation in Local Large Language Model Agents","created":"2026-07-01","cited_by_count":0,"area":"agents"},{"id":"2609.14976","title":"MemRiskBench: Trace-Aware Risk-Preserving Evaluation for Long-Horizon LLM Agents","created":"2026-09-14","cited_by_count":0,"area":"agents"},{"id":"2609.20734","title":"On-Demand Attention: Language Models Know When to Recall","created":"2026-09-17","cited_by_count":0,"area":"agents"},{"id":"2609.26219","title":"PatchKV: Efficient KV Cache Recovery for Dynamically Edited LLM Contexts","created":"2026-08-18","cited_by_count":0,"area":"agents"},{"id":"2609.27606","title":"State-Grounded Conditioning: Wrapping User-Facing LLM Agents Where Direction Depends on Live State","created":"2026-09-23","cited_by_count":0,"area":"agents"},{"id":"2609.32259","title":"Prefill-Free Cross-Family KV Cache Transfer for Heterogeneous Multi-Agent LLMs","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"id":"2609.38712","title":"Staying on Task: Testing the Foundations of Long-Horizon Agent Reliability","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2609.39068","title":"SparseEngine: Sparse-First Inference Engine","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.00316","title":"DuplexSpeechBench-Document Grounding: Benchmarking Document Grounding and Hallucinations in Voice Agents","created":"2026-09-29","cited_by_count":0,"area":"agents"}],"next_cursor":"100"}