{"total":30,"rows":[{"id":"2608.17310","title":"Agentic ESOpt: Fine-Tuning Long-Horizon LLM Agents with Minimal GPU Requirements","created":"2026-08-18","cited_by_count":3,"area":"agents"},{"id":"2609.20784","title":"RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning","created":"2026-09-17","cited_by_count":3,"area":"agents"},{"id":"2608.02441","title":"Agentic Commerce World: An Auditable and Verifiable Environment for Vibe Commerce","created":"2026-08-03","cited_by_count":1,"area":"agents"},{"id":"2609.24526","title":"ME-VLM: A Unified VLM for Embodied Cognition and Agent Coordination","created":"2026-09-21","cited_by_count":1,"area":"agents"},{"id":"2609.32577","title":"Groupwise Agentic Grading and Advantage Redistribution for Code Agent RL","created":"2026-09-26","cited_by_count":1,"area":"agents"},{"id":"2609.13356","title":"ZGCM-1: A Fully Open and Extremely Efficient Foundation Model for Math and Agentic Search","created":"2026-09-11","cited_by_count":0,"area":"agents"},{"id":"2609.25192","title":"FinFIRST: Benchmarking Search Agents for Financial Information Retrieval, Sourcing and Traceability","created":"2026-09-21","cited_by_count":0,"area":"agents"},{"id":"2609.26777","title":"SWE-Serve: Benchmarking Agentic Engineering For Production Inference Serving","created":"2026-09-22","cited_by_count":0,"area":"agents"},{"id":"2609.29773","title":"Breaking the Environment Wall: Evolving LLM Agent Environments for Recursive Self-Improvement","created":"2026-09-24","cited_by_count":0,"area":"agents"},{"id":"2609.33807","title":"CodeActionBench: Evaluating Agentic Code-as-Policy for Embodied Manipulation","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2609.35909","title":"Cheap to Hypothesize, Costly to Verify: The Defense Surface of Agentic Vulnerability Discovery","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.35912","title":"MMSkillRisk: Can Agents Stay Safe When Multimodal Skills Become Traps?","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.38335","title":"E2E-SWE: Benchmarking LLMs on Building Working Codebases from Scratch","created":"2026-09-29","cited_by_count":0,"area":"agents"},{"id":"2609.38891","title":"Consistent Plan-Act for Long-Horizon Agentic Tasks","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2609.39325","title":"WorkGenesis: Building the Worlds That Teach Agents to Work","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2609.40253","title":"ComputerSD: Online Self-Distillation from Real-Time Feedback for Computer-Use Agents","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2609.40284","title":"cua-speedrun: Standardized Benchmarking of the Speed of Computer-Use Agents","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.06563","title":"HERA: Harness-Environment Co-Evolution for Reliable Agentic Abstention","created":"2026-10-05","cited_by_count":0,"area":"agents"},{"id":"2610.07792","title":"ServeLearnBench: How Well Can Agents Self-Improve from Serving Experience?","created":"2026-10-06","cited_by_count":0,"area":"agents"},{"id":"2610.08076","title":"SpeedrunBench: Challenging LLM Agents with Video Game Speedrunning","created":"2026-10-06","cited_by_count":0,"area":"agents"},{"id":"2610.08102","title":"DSV-Mem: Evaluating Multimodal Memory in Professional Workflows for MLLM Agents","created":"2026-10-06","cited_by_count":0,"area":"agents"},{"id":"2610.08630","title":"Towards In-Parameter Memory Augmentation for Large Language Models","created":"2026-10-06","cited_by_count":0,"area":"agents"},{"id":"2610.09374","title":"DUDA-Bench: Benchmarking LLM Agents on Multimodal Data-Driven Urban Diagnosis","created":"2026-10-07","cited_by_count":0,"area":"agents"},{"id":"2610.10478","title":"Before They Can Solve: Predicting Post-Training Coding-Agent Performance from Base Models","created":"2026-10-07","cited_by_count":0,"area":"agents"},{"id":"2610.11552","title":"Safe, Persistent, and Evolving Agent Harness for Understanding Partially Observable Worlds","created":"2026-10-08","cited_by_count":0,"area":"agents"},{"id":"2610.11773","title":"Safe Actions Alone Do Not Ensure Safe Agents: Identifying Unfulfilled Obligations with Guard Models","created":"2026-10-08","cited_by_count":0,"area":"agents"},{"id":"2610.12183","title":"A Closer Look at Agentic BBO: Benchmarking LLM Agents for Black-Box Optimization","created":"2026-10-08","cited_by_count":0,"area":"agents"},{"id":"2610.14405","title":"SPROUT: Scaling Agentic Reinforcement Learning for Long-Horizon Software Engineering","created":"2026-10-09","cited_by_count":0,"area":"agents"},{"id":"2610.16592","title":"Prorsa: Unleashing the Potential of Prefill-Decode Disaggregation in Agentic Reinforcement Learning","created":"2026-10-12","cited_by_count":0,"area":"agents"},{"id":"2610.20344","title":"Doc2Harness: Benchmarking LLMs on Long-Horizon Harness Engineering of Coding Agents","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}