Understand this story
On November 9, 2026, Baidu released the automated research system ERNIE Evolve, used to improve AI training and inference. After being given a research goal, the system autonomously selects research directions, modifies code, and runs experiments; only improvements that pass independent evaluation and review are retained, and the results of each round are used to guide the next round. Baidu says that ERNIE Evolve achieved SOTA on NanoChat AutoResearch and NanoGPT Speedrun, and in ERNIE 5.5 Flash inference tests it increased deterministic GPU inference throughput by 33.7% and single-request decoding speed by 14.9%. Baidu says this is a step toward recursive self-improvement (RSI), and that the next step is to extend the method to training systems, model capabilities, and evaluation. On the same day, QbitAI reported that Baidu ERNIE disclosed RSI progress for the first time, and that ERNIE Evolve has been used for inference optimization of ERNIE 5.5 Flash, including performance optimization for low-latency scenarios on Kunlun Core P800, deterministic inference throughput optimization, and extreme decoding speed optimization; the report also mentioned that Baidu open-sourced ERNIE 5.5 Flash Base on November 5.
AI-generated from public reports
Latest development · Report
Baidu Releases ERNIE Evolve Automated Research System, GPU Inference Throughput Up 33.7%Developments
1 confirmed developments
- Source:English text is being prepared.
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Nov 9
Baidu BaiduFirst-partySelected
Baidu Releases ERNIE Evolve Automated Research System, GPU Inference Throughput Up 33.7%
Baidu has released the ERNIE Evolve automated research system for improving AI training and inference: given a research goal, it selects research directions, modifies code, and runs experiments; only improvements that pass independent evaluation and review are retained, and the results of each round guide the next round. The system achieved SOTA on NanoChat AutoResearch and NanoGPT Speedrun, and in ERNIE 5.5 Flash inference tests it improved deterministic GPU inference throughput by 33.7% and single-request decoding speed by 14.9%. Baidu calls this a step toward recursive self-improvement (RSI), and its next step is to extend the method to training systems, model capabilities, and evaluation.
QbitAI
Baidu ERNIE Discloses RSI Progress for the First Time; ERNIE Evolve Has Been Used in ERNIE 5.5 Flash R&D
Baidu ERNIE discloses RSI progress for the first time, unveiling the automated research system ERNIE Evolve that participated in the R&D of ERNIE 5.5 Flash. The system can autonomously propose research directions, conduct experiments, verify results, and accumulate experience. On the three evaluation metrics across the two tasks NanoChat AutoResearch and NanoGPT Speedrun, ERNIE Evolve achieved the current publicly verified SOTA performance, and has already been used for inference optimization of ERNIE 5.5 Flash, including performance optimization for low-latency scenarios on Kunlunxin P800, deterministic inference throughput optimization, and extreme decoding speed optimization. Baidu open-sourced ERNIE 5.5 Flash Base on November 5, and a person close to Baidu revealed that the new ERNIE model may be released soon.
Leiphone
Baidu ERNIE discloses RSI progress: ERNIE Evolve has been used in the development of ERNIE 5.5 Flash
Baidu ERNIE has for the first time disclosed its automated research system ERNIE Evolve. The system can autonomously propose research directions, conduct experiments, and verify results, and has already been used for inference optimization of the soon-to-be-released ERNIE 5.5 Flash. In low-latency scenario optimization on the Kunlunxin P800, ERNIE Evolve took about 168 hours to raise generation speed to 623.6% of the baseline; deterministic inference throughput optimization raised throughput to 133.7% of the baseline. The system achieved publicly verified SOTA performance on three evaluation metrics across the two tasks NanoChat AutoResearch and NanoGPT Speedrun, and Baidu open-sourced ERNIE 5.5 Flash Base on November 5.
Heat trend for this story
- Current
- 16
- Period peak
- 26 Nov 10 00:00
- 24-hour change
- —
Move the pointer or select the chart to inspect hourly heat. Use the left and right arrow keys with a keyboard.