{"total":71,"rows":[{"id":"2603.10165","title":"OpenClaw-RL: Train Any Agent Simply by Talking","created":"2026-03-10","cited_by_count":90,"area":"agents"},{"id":"2605.21384","title":"SpecBench: Measuring Reward Hacking in Long-Horizon Coding Agents","created":"2026-05-20","cited_by_count":28,"area":"agents"},{"id":"2604.11641","title":"CodeTracer: Towards Traceable Agent States","created":"2026-04-13","cited_by_count":16,"area":null},{"id":"2606.22995","title":"Group-Graph Policy Optimization for Long-Horizon Agentic Reinforcement Learning","created":"2026-06-22","cited_by_count":13,"area":"agents"},{"id":"2604.04356","title":"REAM: Merging Improves Pruning of Experts in LLMs","created":"2026-04-06","cited_by_count":10,"area":"moe"},{"id":"2604.08000","title":"PASK: Toward Intent-Aware Proactive Agents with Long-Term Memory","created":"2026-04-09","cited_by_count":9,"area":null},{"id":"2606.03854","title":"CLI-Anything: Towards Agent-Native Computer Use","created":"2026-06-02","cited_by_count":9,"area":"lr"},{"id":"2605.15040","title":"Orchard: An Open-Source Agentic Modeling Framework","created":"2026-05-14","cited_by_count":8,"area":"agents"},{"id":"2606.26300","title":"The Verification Horizon: No Silver Bullet for Coding Agent Rewards","created":"2026-06-24","cited_by_count":8,"area":"agents"},{"id":"2605.12913","title":"Revisiting DAgger in the Era of LLM-Agents","created":"2026-05-13","cited_by_count":7,"area":"agents"},{"id":"2607.12385","title":"PM-Bench: Evaluating Prospective Memory in LLM Agents","created":"2026-07-14","cited_by_count":7,"area":"agents"},{"id":"2606.14502","title":"From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI","created":"2026-06-12","cited_by_count":6,"area":null},{"id":"2608.09802","title":"SWE-Bench ProMax: Benchmarking Agents on Large-Scale Multilingual Code Refactoring","created":"2026-08-10","cited_by_count":6,"area":"agents"},{"id":"2609.20804","title":"An Empirical Study of Harness Design for Coding Agents","created":"2026-09-17","cited_by_count":6,"area":"agents"},{"id":"2604.04443","title":"DeonticBench: A Benchmark for Reasoning over Rules","created":"2026-04-06","cited_by_count":5,"area":"lr"},{"id":"2605.08301","title":"Priming: Hybrid State Space Models From Pre-trained Transformers","created":"2026-05-08","cited_by_count":5,"area":null},{"id":"2605.19660","title":"OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond","created":"2026-05-19","cited_by_count":5,"area":"inference"},{"id":"2606.00408","title":"Masking Stale Observations Helps Search Agents -- Until It Doesn't: A Regime Map and Its Mechanism","created":"2026-05-29","cited_by_count":5,"area":null},{"id":"2606.15378","title":"Rethinking the Role of Efficient Attention in Hybrid Architectures","created":"2026-06-13","cited_by_count":5,"area":"lr"},{"id":"2603.25226","title":"WebTestBench: Evaluating Computer-Use Agents towards End-to-End Automated Web Testing","created":"2026-03-26","cited_by_count":4,"area":"agents"},{"id":"2603.25804","title":"RealChart2Code: Advancing Chart-to-Code Generation with Real Data and Multi-Task Evaluation","created":"2026-03-26","cited_by_count":4,"area":"mllm"},{"id":"2605.17862","title":"$\\boldsymbol{f}$-OPD: Stabilizing Long-Horizon On-Policy Distillation with Freshness-Aware Control","created":"2026-05-18","cited_by_count":4,"area":"distill"},{"id":"2605.19932","title":"PEEK: Context Map as an Orientation Cache for Long-Context LLM Agents","created":"2026-05-19","cited_by_count":4,"area":"agents"},{"id":"2607.00341","title":"DiscoLoop: Looping Discrete Embeddings and Continuous Hidden States for Multi-hop Reasoning","created":"2026-07-01","cited_by_count":4,"area":"lr"},{"id":"2607.09375","title":"Mach-Mind-4-Flash Technical Report","created":"2026-07-10","cited_by_count":4,"area":"agents"},{"id":"2609.08183","title":"NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness","created":"2026-09-08","cited_by_count":4,"area":"agents"},{"id":"2603.17973","title":"TDAD: Test-Driven Agentic Development - Reducing Code Regressions in AI Coding Agents via Graph-Based Impact Analysis","created":"2026-03-18","cited_by_count":3,"area":"agents"},{"id":"2604.14004","title":"Memory Transfer Learning: How Memories are Transferred Across Domains in Coding Agents","created":"2026-04-15","cited_by_count":3,"area":"agents"},{"id":"2604.16625","title":"AdaExplore: Failure-Driven Adaptation and Diversity-Preserving Search for Efficient Kernel Generation","created":"2026-04-17","cited_by_count":3,"area":null},{"id":"2605.27472","title":"AssertLLM2: A Comprehensive LLM Benchmark for Assertion Generation from Design Specifications","created":"2026-05-26","cited_by_count":3,"area":null},{"id":"2606.15532","title":"EIBench: A Simulator-Based Benchmark and Turn-Credit RL for Emotion Management","created":"2026-06-14","cited_by_count":3,"area":"lr"},{"id":"2608.25776","title":"EVOMAL: Self-Poisoning in Self-Evolving Coding Agents","created":"2026-08-26","cited_by_count":3,"area":"agents"},{"id":"2606.30562","title":"Morphing into Hybrid Attention Models","created":"2026-06-29","cited_by_count":2,"area":null},{"id":"2606.31315","title":"BlockPilot: Instance-Adaptive Policy Learning for Diffusion-based Speculative Decoding","created":"2026-06-30","cited_by_count":2,"area":"inference"},{"id":"2608.09123","title":"RISE-RL: Rubric-Informed Selective Exploration for Open-Ended Reinforcement Learning","created":"2026-08-10","cited_by_count":2,"area":"alignment"},{"id":"2608.12149","title":"Massive Activations in Hybrid Linear Attention Large Language Models: Pre-Attention Spikes and Inter-Spike Plateaus","created":"2026-08-12","cited_by_count":2,"area":null},{"id":"2603.17456","title":"Stage-Aware Communication Scheduling for Disaggregated LLM Serving","created":"2026-03-18","cited_by_count":1,"area":"inference"},{"id":"2605.03195","title":"Terminus-4B: Can a Smaller Model Replace Frontier LLMs at Agentic Execution Tasks?","created":"2026-05-04","cited_by_count":1,"area":"agents"},{"id":"2605.20075","title":"CopT: Contrastive On-Policy Thinking with Continuous Spaces for General and Agentic Reasoning","created":"2026-05-19","cited_by_count":1,"area":"lr"},{"id":"2607.21971","title":"Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning","created":"2026-07-24","cited_by_count":1,"area":"lr"},{"id":"2607.25130","title":"Learning from 53.6K Real-World Developer Edits of AI-Generated Code","created":"2026-07-27","cited_by_count":1,"area":null},{"id":"2608.21962","title":"NoTB: Oracle-Free Triage of LLM-Generated RTL via Cross-Model Formal Consensus","created":"2026-08-22","cited_by_count":1,"area":null},{"id":"2610.08077","title":"Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresight","created":"2026-10-06","cited_by_count":1,"area":null},{"id":"2605.14084","title":"CRANE: Constrained Reasoning Injection for Code Agents via Nullspace Editing","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.20936","title":"DASH: Fast Differentiable Architecture Search for Hybrid Attention in Minutes on a Single GPU","created":"2026-05-20","cited_by_count":0,"area":"inference"},{"id":"2605.27531","title":"Agentic Separation Logic Specification Synthesis","created":"2026-05-26","cited_by_count":0,"area":"agents"},{"id":"2605.28734","title":"Code as a Weapon: A Consensus-Labeled Prompt Bank for Measuring Coding-Model Compliance with Malicious-Code Requests","created":"2026-05-27","cited_by_count":0,"area":"safety"},{"id":"2605.28965","title":"Frontier LLM-based agents can overcome the ontology curation bottleneck for natural phenotypes","created":"2026-05-27","cited_by_count":0,"area":"agents"},{"id":"2606.24901","title":"LLM Evolution as an Industry-Scale Ecosystem: A Lifecycle Perspective on Continual Learning","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2606.26132","title":"Code evolution for link prediction in complex networks","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2606.31159","title":"An Empirical Study of Security Calibration in Large Language Models for Code","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.00440","title":"Minos: A Multi-Agent Collaborative Framework for Provenance-Based Backward Tracking","created":"2026-07-01","cited_by_count":0,"area":"agents"},{"id":"2607.21677","title":"Enhancing SLMs for Sustainable Code Optimization in Radio-Astronomy","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2608.09898","title":"Consilience for Verifier-Free Test-Time Scaling","created":"2026-08-10","cited_by_count":0,"area":"lr"},{"id":"2608.21775","title":"No One Model Catches Every Harm: Benchmarking Content Moderation Across Safety Scenarios","created":"2026-08-22","cited_by_count":0,"area":"safety"},{"id":"2608.25276","title":"Groundhog Bit-Flip Attack: Seeding Infinite Generation Loops in Mixture-of-Experts LLMs through Bit Flips","created":"2026-08-26","cited_by_count":0,"area":"moe"},{"id":"2609.08418","title":"Feyospace-v1: How the Cyber Mercury Seven Trained Frontier Cyber Models","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.16648","title":"GrowMTP: Can RL Grow Its Own Draft Head?","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.19970","title":"CellRFT: Reinforcement Fine-Tuning for Single-Cell Perturbation Modeling","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.32493","title":"SoFT: Soft Targets for Generalizable LLM Fine-Tuning","created":"2026-09-26","cited_by_count":0,"area":"distill"},{"id":"2609.33243","title":"CodeSkill: Latent Skill Abstraction for Long-Horizon Code Agents","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2609.34380","title":"DPS: Dual-Mode Precision LLM Serving with Semi-Unified Memory","created":"2026-09-28","cited_by_count":0,"area":"inference"},{"id":"2609.35568","title":"From Experience to Expertise: Adoption-Aware Memory Learning for Data-Scarce NPU Kernel Synthesis","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.01519","title":"Auto-Formalizing Neuro-Symbolic Predictors","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.02206","title":"KaliBench: A Fine-Grained Benchmark for Cybersecurity Tool Use on Kali Linux with Runtime-Free Verifiable Rewards","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.03199","title":"Predicting and Repairing Merge Collapse in Large Language Models","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.11593","title":"Runnable Commit Untangling for Coding Agents","created":"2026-10-08","cited_by_count":0,"area":"agents"},{"id":"2610.13395","title":"ProgramGym: Scaling Training Environments for Long-Horizon Program Reproduction Agents","created":"2026-10-09","cited_by_count":0,"area":"agents"},{"id":"2610.13479","title":"A Local Agentic AI Framework to Generate Edge Case Scenarios for Safety Assurance","created":"2026-10-09","cited_by_count":0,"area":"agents"},{"id":"2610.13735","title":"Orthros: Phase-Aware Heterogeneous Attention for Efficient Transformers","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.15894","title":"Make Every Expansion Count: Learning to Search Efficiently in LLM Code Repair","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}