Interaction ≠ Endorsement. FLAP is an open launch platform. We provide onboarding, technical support, and product guidance to projects building with us, but this should never be interpreted as an endorsement, partnership, investment, or involvement in the project's operations. We love supporting builders and helping them get started. That's what we're here for. Any project claiming to be "officially endorsed by FLAP" or "backed by FLAP" is making a false claim and should be treated as a scam. 🦋

Every interaction your deployed AI agent handles could double as training data to make it smarter. That is the pitch of this paper. NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness 🧩 Overview The authors turn logs from a "routing harness" (the layer that decides which capability tier handles each request) directly into training data, with no extra synthetic data pipeline, to recursively improve the model. ❓ The problem it solves Recursive self-improvement needs a way for a system to observe its own capabilities and feed that back into training. Most approaches build a separate data pipeline for this, but the material is already sitting inside everyday routing logs. ⚙️ Method Execution trajectories are structured by user turn, quality-checked with six semantic dimensions plus structural validation, and routing scores are used to order a three-stage curriculum for both SFT and on-policy distillation. Evaluation results then steer the next batch of training data toward weak spots. 📊 Results Across 10 agentic, coding, and instruction-following benchmarks, the 4B model's macro-average rose from 58.94 to 64.87, and the 9B model from 65.60 to 69.04, beating public synthetic data by +6.26 macro-average points. #AIAgents# #SelfImprovement#

Strangest interaction in France so far. Ordering a sparkling water in a bar. Barman looking puzzled at his 250 bottles of alcohol. Serves sparkling water. Doesn't have an entry for water in his cash register. Euh… Shall we say… 1 euro?