arXiv:2608. 06144v1 Announce Type: new Abstract: Most agent benchmarks evaluate tasks independently and cannot measure whether experience from one task helps with later tasks.
arXiv:2608. 04077v1 Announce Type: new Abstract: Evaluating financial AI agents requires criteria aligned with real professional work.
arXiv:2607. 05297v1 Announce Type: new Abstract: Recent LLM agents tackle increasingly long-horizon, open-ended tasks, and external skills, reusable procedural knowledge supplied to the agent, further extend this capability.
arXiv:2608. 02636v1 Announce Type: cross Abstract: Self-evolving skill systems promise to improve agents by turning execution feedback into persistent skill updates without changing the underlying model.
arXiv:2606. 14239v1 Announce Type: new Abstract: Agent skills are structured procedural packages that guide frozen LLM agents in specialized workflows.
arXiv:2608. 03764v1 Announce Type: new Abstract: Agent self-evolution updates an agent's persistent state from prior experience and reuses it to solve related tasks more effectively.
arXiv:2607. 25891v1 Announce Type: new Abstract: Evaluating AI agents in interactive environments is hindered by fragmented tasks, scaffolds, verifiers, and scoring rules.
arXiv:2605. 17554v2 Announce Type: replace Abstract: Frontier deep research agents (DRAs) plan a research task, synthesize across documents, and return a structured deliverable on demand.
arXiv:2605. 14355v3 Announce Type: replace Abstract: As AI agents improve, the central question is no longer whether they can solve isolated well-defined financial tasks, but whether they can reliably carry out financial professional work.
arXiv:2607. 25398v1 Announce Type: new Abstract: Language-model agents are increasingly deployed under standing instructions: a system prompt, a policy file, or a skills document is placed in context, and the agent is trusted to let it govern every action that follows.
arXiv:2608. 17684v1 Announce Type: new Abstract: Self-evolving agents turn experience into reusable skills, workflows, or memories, but post-evolution accuracy alone does not show whether learned behavior preserves previously correct behavior or security.
arXiv:2607. 17044v1 Announce Type: cross Abstract: Multi-step enterprise agent tasks fail in a characteristic way: single-pass inference has no checkpoint between deciding an answer and committing to it.
arXiv:2606. 01314v1 Announce Type: new Abstract: Recent self-evolving agents have shown that skills can be discovered, refined, and accumulated through execution.