← October 30, 2026 briefing · added in the 20:00 KST update
Tsinghua, Infinigence AI and AgiBot present method for 96 real robots to learn from each other's experience; newly added robots reach 97.5% success (report)
Announced October 30, 2026
Verified (fact)
According to Pandaily and QbitAI (量子位), a joint team from Tsinghua University, Infinigence AI and AgiBot introduced a method (Collective Experience Learning) in which 96 real robots learn by sharing their task experience with one another. Instead of relying on human demonstrations, the approach has robots teach each other. Two robots that did not take part in training reportedly achieved a 97.5% success rate over 600 attempts, and the success rate on a phone-packaging task rose from 79.2% to 98.3%.
Needs fact-check (claim)
The success rates were reported as the research team's experimental results; external replication has not been confirmed.
Why it matters (interpretation)
A key bottleneck for embodied AI is the cost of data that humans must collect by hand. Reusing the experience of robot fleets deployed in the field as training data could create a setup where performance improves as the number of robots grows.
Confidence medium · official source pending
Sources
More about Tsinghua University
-
Tsinghua and Zhejiang's 'Algebraic World Model' formalizes ARC-AGI-3 game rules in Lean 4, proving six sealed levels are 'unsolvable' (report)
According to Pandaily, the Algebraic World Model (AWM) from researchers at Tsinghua University and Zhejiang University learns the rules...
-
Tsinghua and Zhipu's 'HarnessPro' lets agents rewrite their own harness from execution logs, claims 26.1% lower cost per task (report)
Researchers from Tsinghua University, Zhipu AI and others introduced 'HarnessPro.' In this approach, an agent analyzes its own execution...
-
Tsinghua develops 588g autonomous liver ultrasound robot that learned doctors' probe handling, evaluated on 119 people (report)
According to AI Times Korea (인공지능신문), researchers at Tsinghua University's School of Biomedical Engineering trained AI on skilled...
-
Tsinghua's THUNLP, ModelBest and OpenBMB release open-source agent OS 'PilotDeck 2.0', with directly viewable and editable memory and lightweight models for easy subtasks (report)
According to Pandaily, Tsinghua University's THUNLP, ModelBest and OpenBMB have released 'PilotDeck 2.0', an open-source agent operating...