conftrace_

real-world task

4 papers

Explore in graph

Co-occurring keywords

benchmark evaluation (1556) agent system (324) large language model (13587) multimodal learning (4645) tool agent (3) multimodal input (11) task execution (13) spreadsheet manipulation (1) table understanding (132) multi-round inference (1)

Papers

Agent-RewardBench: Towards a Unified Benchmark for Reward Modeling across Perception, Planning, and Safety in Real-World Multimodal Agents ACL 2025
GTA: A Benchmark for General Tool Agents NIPS 2024
SpreadsheetBench: Towards Challenging Real World Spreadsheet Manipulation NIPS 2024
CRoW: Benchmarking Commonsense Reasoning in Real-World Tasks EMNLP 2023