DAYJOB is a new benchmark comprising 130 long‑horizon professional tasks created by experts in healthcare (50 tasks) and finance (80 tasks). Each task is packaged as a containerized Harbor environment and evaluated against a detailed binary rubric, requiring agents to meet every criterion to pass. In tests across 30 model configurations, the best model (Claude Opus 5.5) achieves about 24% success in both domains, while the median model scores below 3%.
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. 06144v1 Announce Type: new Abstract: Most agent benchmarks evaluate tasks independently and cannot measure whether experience from one task helps with later tasks.
KnowBench is a new benchmark for clinical AI that measures Effort Reduction (ER), the proportion of system-generated clinical work product accepted by clinicians after expert and safety review. The metric is applied uniformly across various administrative tasks—visit notes, billing codes, orders, EHR summarization, patient summaries, and decision support—using the clinician’s review-and-attestation as ground truth. An initial deployment of Knowtex’s models achieved an aggregate ER of 97.99% across more than one million encounters in six months, with specialty-specific ER ranging from 96.8% to 98.9%.
arXiv:2606. 03918v1 Announce Type: new Abstract: AI agents can increasingly handle the mechanical tasks of financial analysis: retrieving documents, calculating formulas, updating spreadsheets.
arXiv:2609.39325v1 Announce Type: new Abstract: The ability of Large Language Model (LLM) agents to complete daily and professional work is receiving increasing attention. Training such agents requir...
arXiv:2608. 04077v1 Announce Type: new Abstract: Evaluating financial AI agents requires criteria aligned with real professional work.
arXiv:2607. 27853v2 Announce Type: replace-cross Abstract: Powered by advances in LLMs and autonomous agents, deep research has become one of the most widely adopted agentic products.
Legal Research Bench (LRB) is a new benchmark comprising 413 open-ended U.S. legal research questions, each paired with a gold answer, supporting authorities, and a binary grading rubric. The study evaluates thirteen advanced language‑model agents using web search, case‑law search, page parsing, and retrieval tools, scoring responses only when all required criteria are met and cited authorities verify. Results show that even the best model, Claude Opus 4.8, achieves full correctness on only 42.9% of questions, with performance varying by legal area and task complexity, and no clear link between more tool calls or inference cost and higher accuracy.
arXiv:2609.23806v1 Announce Type: new Abstract: Many knowledge-work benchmarks are constructed around individual tasks, with the context needed for each task selected together with or after the task...
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. 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:2606. 03829v1 Announce Type: new Abstract: Financial-research answers are decision-relevant only when another analyst can audit how they were produced: which source was chosen, which period and accounting definition were used, which assumptions were made, and how the calculation was performed.