REVIEW 11 cited by
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
OfficeBench: Benchmarking Language Agents across Multiple Applications for Office Automation
read the original abstract
Office automation significantly enhances human productivity by automatically finishing routine tasks in the workflow. Beyond the basic information extraction studied in much of the prior document AI literature, the office automation research should be extended to more realistic office tasks which require to integrate various information sources in the office system and produce outputs through a series of decision-making processes. We introduce OfficeBench, one of the first office automation benchmarks for evaluating current LLM agents' capability to address office tasks in realistic office workflows. OfficeBench requires LLM agents to perform feasible long-horizon planning, proficiently switch between applications in a timely manner, and accurately ground their actions within a large combined action space, based on the contextual demands of the workflow. Applying our customized evaluation methods on each task, we find that GPT-4 Omni achieves the highest pass rate of 47.00%, demonstrating a decent performance in handling office tasks. However, this is still far below the human performance and accuracy standards required by real-world office workflows. We further observe that most issues are related to operation redundancy and hallucinations, as well as limitations in switching between multiple applications, which may provide valuable insights for developing effective agent frameworks for office automation.
Forward citations
Cited by 11 Pith papers
-
TUA-Bench: A Benchmark for General-Purpose Terminal-Use Agents
TUA-Bench provides 120 manually designed terminal tasks across five families with execution-based scoring; the top agent reaches 65.8% success.
-
ClawsBench: Evaluating Capability and Safety of LLM Productivity Agents in Simulated Workspaces
ClawsBench is a benchmark using high-fidelity mock services to evaluate LLM agents on 44 productivity tasks, finding 39-64% success rates and 7-33% unsafe action rates depending on scaffolding.
-
PolyWorkBench: Benchmarking Multilingual Long-Horizon LLM Agents
A 67-task multilingual long-horizon agent benchmark across five workplace domains reports large drops versus monolingual settings and attributes them to compounding language-reasoning failures.
-
OSWorld2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks
OSWorld 2.0 is a benchmark of 108 realistic long-horizon computer-use tasks where current agents achieve only 20.6% binary completion, struggling with state inference and constraint tracking.
-
Signal-Driven Observation for Long-Horizon Web Agents
Signal-Driven Observation decouples observation from action frequency in long-horizon web agents by invoking selective task-relevant DOM reads only on signals such as URL changes or action failures.
-
BlueFin: Benchmarking LLM Agents on Financial Spreadsheets
BlueFin is a new benchmark for LLM agents on financial spreadsheets showing frontier models score below 50% with weaknesses in dynamic correctness.
-
PREPING: Building Agent Memory without Tasks
Preping builds agent memory via proposer-guided synthetic practice and selective validation, matching offline/online methods at 2-3x lower deployment cost.
-
Augmenting Interface Usability Heuristics for Reliable Computer-Use Agents
Augmented Nielsen heuristics improve computer-use agent task completion on varied interfaces while preserving human usability, as shown in UI-Verse experiments and human studies.
-
Finch: Benchmarking Finance & Accounting across Spreadsheet-Centric Enterprise Workflows
Finch is a new benchmark with 172 composite workflows and 384 tasks from real enterprise data that shows top AI models like GPT-5.1 Pro pass only 38.4% of workflows under human evaluation.
-
A Comprehensive Survey of Agents for Computer Use: Foundations, Challenges, and Future Directions
A survey of 87 agents for computer use and 33 datasets that introduces a three-dimensional taxonomy across domain, interaction, and agent perspectives and identifies six research gaps.
-
Agentic Performance at the Edge: Insights from Benchmarking
Edge agentic AI quality is not a simple function of model size; robust results require joint design of model selection and tool integration, as revealed by domain-conditioned benchmarks showing accuracy-latency Pareto fronts.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.