{"total":18,"rows":[{"id":"2608.09096","title":"Evo-Bench: Can Language Models Improve Agent Harness?","created":"2026-08-10","cited_by_count":11,"area":"agents"},{"id":"2607.27155","title":"OmegaUse-OfficeVal: Benchmarking LLM Agents on Long-Horizon Office-Suite Tasks with Economic Grounding","created":"2026-07-29","cited_by_count":2,"area":"agents"},{"id":"2608.17597","title":"HarnessRisk: A Lifecycle-Oriented Benchmark for Agent Harness Safety","created":"2026-08-18","cited_by_count":2,"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":"2610.04262","title":"CADForge: Agentic Single-View CAD Reconstruction with Explicit Geometry Reasoning","created":"2026-10-03","cited_by_count":1,"area":"agents"},{"id":"2607.26410","title":"Voice Memory for Agentic Speech Recognition","created":"2026-07-29","cited_by_count":0,"area":"agents"},{"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":"2608.29310","title":"Super Library Agent: Joint Generation and Maintenance of Multiple Applications Beyond the Single Codebase","created":"2026-08-29","cited_by_count":0,"area":"agents"},{"id":"2608.29612","title":"LLMs Interpret, Embeddings Organize, Graphs Emerge: Agent-Driven Compilation of Scientific Knowledge","created":"2026-08-30","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":"2609.27307","title":"Learn How to Act from Your Own Interactions: On-Policy Self-Distillation for GUI Agents","created":"2026-09-23","cited_by_count":0,"area":"agents"},{"id":"2609.33295","title":"TraceDance: An Automated System for Building Agent Behavior Benchmarks from Real-World Agent Deployment Traces","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2609.33470","title":"LiveOption: Evaluating LLM Agents in Structured Option Trading with Nonlinear Payoffs","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2609.40230","title":"EviRover: Reinforcing Agentic Perception Beyond a Glance","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":"2610.08250","title":"MASC: A Multi-Agent Self-Calibration Framework with Latent Construct Alignment for Consistent Client Role-Playing in Psychological Counseling","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":"2610.11188","title":"What to Admit and How to Present: Governing Persistent Memory in LLM Agents","created":"2026-10-08","cited_by_count":0,"area":"agents"}],"next_cursor":null}