Tag: LLM Agents
All the articles with the tag "LLM Agents".
-
How OSWorld Turns Computer Work into an Agent Benchmark
· 35 min readA technical guide to OSWorld's origins, 13 real tasks, Verified, 2.0 and 2.1, scoring contracts, and the experiments needed to distinguish local progress from complete computer work.
-
Can RFT Learn From Failure? Negative Signals for Agent Fine-Tuning
· 16 min readA technical guide to learning from failed agent rollouts through step masking, unlikelihood, DPO, SimPO, and step-level credit assignment.
-
Do LLM Agents Work Equally Well Across Languages?
· 11 min readAgent performance differs across languages, tasks, and localization settings. A visual review of 30 languages and 16 evidence sources identifies where Arabic, Thai, Japanese, and Hindi need targeted evaluation.