English translation is being prepared.
Matched fieldsSummary
←Search results
Search “Microsoft”
Microsoft and City University of Hong Kong propose Taste-Bench to evaluate agent decision-making
Researchers from Microsoft and City University of Hong Kong have built Taste-Bench to evaluate the long-term decision-making capabilities of AI agents on long tasks. The benchmark contains 502 binary-choice questions. According to The Decoder, the best-performing model, GPT-5.6 Sol, achieved an average accuracy of only 59.7%, while GPT-5.5 reached 59.5%. When key clues only become apparent after a large amount of subsequent work, the average accuracy of all models drops to 21%, close to random guessing, and increasing the reasoning budget brings almost no improvement. The researchers also distilled the teacher model's judgments using Qwen3.6-27B as the base model; the student's accuracy on unseen tasks rose from 30% to 47.9%, and its success rate on 41 SWE-bench Pro tasks increased from 14.6% to 33.7%.
Matched fieldsSummary
English translation is being prepared.
Matched fieldsSummary
LG launches group-wide business review meetings
On October 19, LG launched business review meetings covering all subsidiaries, chaired by Chairman Koo Kwang-mo, to assess 2026 performance and plan for 2027; the meetings will last about one month. According to The Elec, the review will discuss specific business cooperation with Nvidia and Microsoft and follow-up implementation plans, involving AI factories, physical AI, mobility, and AI infrastructure. The report says this is part of LG's "One LG" strategy, aimed at integrating the capabilities of each subsidiary and achieving results in key AI markets. There is currently no qualified factual evidence of further progress.
to assess 2026 performance and plan for 2027; the meetings will last about one month. According to The Elec, the review will discuss specific business cooperation with Nvidia and Microsoft and follow-up implementation plans, involving AI factories, physical AI, mobility, and AI infrastructure. The report says this is part of LG's "One LG" strategy, aimed at integrating the capabilities of each subsidiary and achieving results in key AI markets. There is currently no qualified factual evidence o
Matched fieldsSummary
English translation is being prepared.
Matched fieldsSummary
English translation is being prepared.
Matched fieldsSummary
English translation is being prepared.
Matched fieldsSummary
English translation is being prepared.
Matched fieldsSummary
English translation is being prepared.
Matched fieldsSummary
English translation is being prepared.
Matched fieldsSummary
English translation is being prepared.
Matched fieldsSummary
English translation is being prepared.
Matched fieldsSummary
English translation is being prepared.
Matched fieldsSummary
English translation is being prepared.
Matched fieldsSummary
English translation is being prepared.
Matched fieldsSummary
English translation is being prepared.
Matched fieldsSummary
English translation is being prepared.
Matched fieldsSummary
English translation is being prepared.
Matched fieldsSummary