Explaining AI Agents Through Execution Traces

arXiv:2604.23280v1 Announce Type: new Abstract: AI agents are now running real transactions, workflows, and sub-agent chains across organizational boundaries without continuous

arXiv:2604.05013v1 Announce Type: cross Abstract: Current LLM coding agents are predominantly trained on composite benchmarks (e.g., bug fixing), which often leads to

arXiv:2604.04990v1 Announce Type: cross Abstract: AI coding agents select frameworks, scaffold infrastructure, and wire integrations, often in seconds. These are architectural

arXiv:2605.01604v1 Announce Type: new Abstract: Existing evaluation frameworks for large language models -- including HELM, MT-Bench, AgentBench, and BIG-bench -- are designed for

arXiv:2605.13848v1 Announce Type: new Abstract: Agentic LLM frameworks that rely on prompted orchestration, where the model itself determines workflow transitions, often suffer

arXiv:2603.17445v2 Announce Type: replace Abstract: When a multi-agent system produces an incorrect or harmful answer, who is accountable if execution logs and agent identifiers

arXiv:2605.11556v1 Announce Type: new Abstract: Solving complex long-horizon tasks requires strong planning and reasoning capabilities. Although datasets with explicit

arXiv:2605.08545v1 Announce Type: new Abstract: Agent benchmarks typically report only final outcomes: pass or fail. This threatens evaluation credibility in three ways. First,