{"total":61,"rows":[{"id":"2606.11709","title":"RLCSD: Reinforcement Learning with Contrastive On-Policy Self-Distillation","created":"2026-06-10","cited_by_count":45,"area":"lr"},{"id":"2607.16051","title":"Loop the Loopies!","created":"2026-07-17","cited_by_count":8,"area":"moe"},{"id":"2607.22334","title":"Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization","created":"2026-07-24","cited_by_count":8,"area":"distill"},{"id":"2606.25819","title":"Beyond Function Calling: Benchmarking Tool-Using Agents under Tool-Environment Unreliability","created":"2026-06-24","cited_by_count":7,"area":"agents"},{"id":"2607.21217","title":"ICAE-Bench: Evaluating Coding Agents as Interactive Project Builders","created":"2026-07-23","cited_by_count":6,"area":"agents"},{"id":"2608.09885","title":"SHE: Trajectory-driven Safety Harness Evolution for LLM Agents","created":"2026-08-10","cited_by_count":6,"area":"agents"},{"id":"2606.16285","title":"HiMPO: Hindsight-Informed Memory Policy Optimization for Less-Entangled Credit in Long-Horizon Agents","created":"2026-06-15","cited_by_count":4,"area":null},{"id":"2607.24300","title":"Self-Authored Verification Is Unreliable in Heuristic Self-Improving Agents","created":"2026-07-27","cited_by_count":4,"area":"synth"},{"id":"2608.02287","title":"SKT: Skill-Use Training at Scale via Verified Synthetic Data Generation","created":"2026-08-03","cited_by_count":3,"area":"agents"},{"id":"2608.03624","title":"LoopMTP: A looped transformer guided by latent multi-token prediction","created":"2026-08-04","cited_by_count":3,"area":null},{"id":"2605.28108","title":"Ask Now, Use Later: Benchmarking the Proactivity Gap in Long-Lived LLM Agents","created":"2026-05-27","cited_by_count":2,"area":"agents"},{"id":"2606.16140","title":"VibeThinker-3B: Exploring the Frontier of Verifiable Reasoning in Small Language Models","created":"2026-06-15","cited_by_count":2,"area":"lr"},{"id":"2606.31564","title":"ACE: Pluggable Adaptive Context Elasticizer across Agents","created":"2026-06-30","cited_by_count":2,"area":"agents"},{"id":"2608.02407","title":"Antares: Foundation Models for Agentic Vulnerability Localization","created":"2026-08-03","cited_by_count":2,"area":"agents"},{"id":"2608.26372","title":"Knowledge-Verified Emergent Deception in LLM Agents Under Conflicting Incentives","created":"2026-08-26","cited_by_count":2,"area":"agents"},{"id":"2608.27287","title":"Astar: Learning to Propose Evolution Directions for Self-Evolving Industrial AI Systems","created":"2026-08-27","cited_by_count":2,"area":"synth"},{"id":"2609.00814","title":"RingMoClaw: An Experience-Inspired Multi-Agent Framework for Self-Evolving Research in Remote Sensing","created":"2026-09-01","cited_by_count":2,"area":null},{"id":"2606.06453","title":"Vortex: Efficient and Programmable Sparse Attention Serving for AI Agents","created":"2026-06-04","cited_by_count":1,"area":"agents"},{"id":"2606.15911","title":"Interactor: Agentic RL oriented Iterative Creation for Ad Description Generation in Sponsored Search","created":"2026-06-14","cited_by_count":1,"area":"agents"},{"id":"2606.23404","title":"ReasoningLens: Hierarchical Visualization and Diagnostic Auditing for Large Reasoning Models","created":"2026-06-22","cited_by_count":1,"area":"lr"},{"id":"2607.18002","title":"ExpertPlex: A High-Goodput Disaggregated Serving System for MoE LLMs with Adaptive Persistent Kernels","created":"2026-07-20","cited_by_count":1,"area":"moe"},{"id":"2608.01652","title":"SyncPlan: Long-Horizon LLM Coordination with Explicit Synchronization and Adaptive Correction","created":"2026-08-03","cited_by_count":1,"area":"agents"},{"id":"2608.04682","title":"Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports","created":"2026-08-05","cited_by_count":1,"area":"agents"},{"id":"2608.18565","title":"SemaPLC: A Project-Grounded, Verification-Gated Agent Harness for PLC Code Generation","created":"2026-08-19","cited_by_count":1,"area":"agents"},{"id":"2609.39223","title":"QATFactory: A Versatile, Deployment-Aligned Framework for Quantization-aware Training and Distillation of LLMs","created":"2026-09-30","cited_by_count":1,"area":null},{"id":"2606.12341","title":"OCELOT: Inference-Leakage Budgets for Privacy-Preserving LLM Agents","created":"2026-06-10","cited_by_count":0,"area":"agents"},{"id":"2606.18613","title":"Are LLMs Ready to Assist Physicians? PhysAssistBench for Interactive Doctor-Patient-EHR Assistance","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2606.20295","title":"Token-Operations-Oriented Inference Optimization Techniques for Large Models","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2607.28439","title":"Beyond a Single Judge: The Evidence-Grounded, Social-Weighted Persona Panel for Generative UI Evaluation","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2607.28478","title":"Would You Walk to the Car Wash? Revealing the Salience Bias of Large Language Models in Commonsense Reasoning","created":"2026-07-30","cited_by_count":0,"area":"lr"},{"id":"2607.29002","title":"MMShopBench: A Real-Log Benchmark for Multimodal, Multi-Turn Shopping Agents","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2608.01862","title":"Wnuan: Staged Post-Training for Question Answering over Proprietary Enterprise Knowledge","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.04156","title":"BrainBench: Benchmarking Large Language Models for Comprehensive EEG Understanding","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.06312","title":"Benchmarking and Enhancing LLMs for Rule-Intensive Review of National Standard Documents","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.07838","title":"Counterfactual Benchmarking and Training for Factuality Consistency and Order-Robust Grounded Reasoning in LLMs over Heterogeneous Knowledge","created":"2026-08-08","cited_by_count":0,"area":"lr"},{"id":"2608.08199","title":"Persuasive and Compliant Tendencies Predict Group Decision-Making in Humans and Language Models","created":"2026-08-08","cited_by_count":0,"area":null},{"id":"2608.13221","title":"TsuGO: Probing Search Efficiency in LLM Reasoning via Go Life-and-Death Problems","created":"2026-08-13","cited_by_count":0,"area":"lr"},{"id":"2608.15064","title":"LongDocBench: Benchmarking TOC Hierarchy and Contextual Relationship Recovery in Long Documents","created":"2026-08-15","cited_by_count":0,"area":null},{"id":"2608.21101","title":"ClawSentry: A Progressive Multi-Tier Security Monitor for Safeguarding Autonomous LLM Agents","created":"2026-08-21","cited_by_count":0,"area":"agents"},{"id":"2608.30703","title":"SingProbe Technical Report","created":"2026-08-31","cited_by_count":0,"area":"safety"},{"id":"2609.03960","title":"FiMI Banking: A Sovereign Model for Indian Retail Banking","created":"2026-09-03","cited_by_count":0,"area":"alignment"},{"id":"2609.06059","title":"DAREBench: Deployment-Aware and Reliable Evaluation of Models as Agents","created":"2026-09-05","cited_by_count":0,"area":"agents"},{"id":"2609.15939","title":"Vulnerability Localization Benchmark: Measuring Agentic Security Analysis at Repository Scale","created":"2026-09-14","cited_by_count":0,"area":"agents"},{"id":"2609.21423","title":"DENSE: Distilling Agent Trajectories into Evidence-Grounded Shortcut Trees for Self-Refinement","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.23363","title":"TicTacBench: Benchmarking Timing Closure Capabilities of Coding Agents","created":"2026-09-20","cited_by_count":0,"area":"agents"},{"id":"2609.25809","title":"You Only Need 2/3 of the Chosen Experts: An Empirical Study of Dynamic Expert Pruning in Fine-Grained MoE LLMs","created":"2026-09-22","cited_by_count":0,"area":"moe"},{"id":"2609.28850","title":"RECLAIM: Can Agents Reproduce the Claims of Machine Learning Papers?","created":"2026-09-23","cited_by_count":0,"area":"agents"},{"id":"2609.31871","title":"IndustryLLM: Failure-Driven LLM Training for Industrial Procurement","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.33585","title":"IVT-Guard: All-in-One Reasoning Model for AI-Generated Content Detection","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2609.35263","title":"WavePP: High-Throughput Pipeline Parallel LLM Prefill under Prefix Reuse","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.35807","title":"Environment Steering: Using Data Flow Control to Improve Agent Utility and Safety","created":"2026-09-19","cited_by_count":0,"area":"agents"},{"id":"2609.38469","title":"The Backdrop Exposes What the World Around an Agent Costs It","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.39068","title":"SparseEngine: Sparse-First Inference Engine","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2609.39661","title":"The Evolution of Attention in Large Language Models: Mechanisms, Trade-offs, and Emerging Trends","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.01127","title":"Counting and Min-Cost Encoding for Tokenization in Large Language Models","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.02425","title":"Finding the Move Is Not Winning the Game: XiangqiBench for Closed-Loop Evaluation of LLM Agents","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.04210","title":"Can LLMs Separate Pasted Artifacts from User Speech? Absorption at Unmarked Prompt Seams","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.16911","title":"Audit tools of the trade: Automated Auditor Elicitation Can Be Sensitive to the Context the Auditor Is Given","created":"2026-10-12","cited_by_count":0,"area":"alignment"},{"id":"2610.19213","title":"PREFER: From Player Experience to Personalized Game Refinement","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.19425","title":"Evaluating Agentic Capabilities Before Post-Training: An End-to-End Approach","created":"2026-10-14","cited_by_count":0,"area":"agents"},{"id":"2610.19458","title":"PFedMA: Who Should Join Next as Federated Multi-Agent Orchestration Evolves?","created":"2026-10-14","cited_by_count":0,"area":"lr"}],"next_cursor":null}