AI News

Microsoft Research Asia news

2 stories about Microsoft Research Asia.

OfficialResearch ·

LongCapHarness boosts frozen models' long-context reasoning without training

Microsoft Research Asia proposes LongCapHarness, which builds a harness around a frozen model rather than post-training it.

Why it matters: Before post-training a small model for long context, teams could try improving the harness around it, which the authors say is cheaper, though a strong harnessing agent is still needed.

1 source
OfficialResearch ·

HarnessMM reuses settled agent decisions to cut HumanEval token use by 87.93%

Researchers from Tsinghua and Microsoft Research Asia report that reusing resolved decisions lifted DeepSeek Harness success on 98 tasks from 71.43% to 85.71%.

Why it matters: Repeated model calls in agent harnesses are a direct cost, so teams may save money before they need a larger model. The authors caution that savings depend on provider cache accounting and on how many actions are already resolved.

1 source