Papers

• PROV-AGENT: Unified Provenance for Tracking AI Agent Interactions in Agentic Workflows (2025)
  Renan Souza et al.
  7.30
• OmegaUse-OfficeVal: Benchmarking LLM Agents on Long-Horizon Office-Suite Tasks with Economic Grounding (2026)
  Jingbo Zhou et al.
  5.85
• AgentTrails: Towards Trust and Reuse for Agentic Tasks (2026)
  Eden Wu et al.
  4.39
• Behavioral Controllability of Agentic Models for Information Extraction: From Fixed Workflows to Reflective Agents (2026)
  Lujia Zhang et al.
  2.00
• The Cost of Knowing: A Resource-Aware Protocol for Benchmarking Hallucination Beyond Static Leaderboards (2026)
  Keyu Li et al.
  2.00
• ClawNet: Human-Symbiotic Agent Network for Cross-User Autonomous Cooperation (2026)
  Zhiqin Yang et al.
  1.94
• Towards a Declarative Agentic Layer for Intelligent Agents in MCP-Based Server Ecosystems (2026)
  Maria Jesus Rodriguez-Sanchez et al.
  1.67