Search results for "BOOST"
2026-04-30
04:54

Perplexity Discloses Web Search Agent Post-Training Method; Qwen3.5-Based Model Outperforms GPT-5.4 on Accuracy and Cost

Perplexity uses SFT followed by RL with Qwen3.5 models, leveraging a multi-hop QA dataset and rubric checks to boost search accuracy and efficiency, achieving best-in-class FRAMES performance. Abstract: Perplexity's post-training workflow for web-search agents combines supervised fine-tuning (SFT) to enforce instruction-following and language consistency with online reinforcement learning (RL) via the GRPO algorithm. The RL stage uses a proprietary multi-hop verifiable QA dataset and rubric-based conversational data to prevent SFT drift, with reward gating and within-group efficiency penalties. Evaluation shows Qwen3.5-397B-SFT-RL achieving top FRAMES performance, 57.3% accuracy with a single tool call and 73.9% with four calls at $0.02 per query, outperforming GPT-5.4 and Claude Sonnet 4.6 on these metrics. Pricing is API-based and excludes caching.
Altro
13:12

UK Inflation Rises to 3.3% in March as Iran War Drives Fuel Prices Higher

UK inflation rose to 3.3% in March, led by fuel prices amid Middle East tensions; petrol and diesel hit new highs, air fares and food rose, clothing fell, keeping inflation above the 2% target. Abstract: March UK inflation reached 3.3%, driven by soaring motor fuel costs linked to Middle East tensions; petrol and diesel price highs, rising airfares and food costs, and falling clothing, signal inflation above the target amid energy-price uncertainty.
Altro