Tether AI Research released BotPsy, a 0.8B-parameter on-device personal assistant built on Qwen3.5-0.8B and post-trained in four stages for tool calling. Against its base model, BFCL v4 rises from 23.4 to 44.0, ACEBench from 30.1 to 58.7 and τ-bench from 23.2 to 51.5; it leads five of six tool-use and agentic benchmarks, trailing only on Claw-Eval behind the 2.5-times-larger Qwen3.5-2B-Think.
Deciding which change is worth trying when a language model improves a language model has depended on costly training experiments. LM2LM uses a frozen LLM as a research world model that predicts a proposal's gain from real experimental records in context, turning those predictions into reinforcement-learning rewards, and periodically executes the current policy's top-rated proposals to write measured outcomes back into the records. Across eight autoregressive and diffusion language-model development environments, Qwen3.8-27B trained this way outperforms GPT-6-sol on held-out tasks, even when GPT-6-sol is given 300 real experimental records in context, at about 33% lower data-generation cost.
This work studies the training stability of full-pipeline FP8 reinforcement learning for LLMs, identifies that compounded FP8 quantization noise distorts the importance ratio so that negative-advantage tokens are over-clipped at the lower bound and their gradients are erroneously zeroed, and proposes Calibrated Clipping, which dynamically realigns clipping bounds by matching the lower-bound clipping quantile of a BF16 reference and rebalancing the upper bound, eliminating entropy surges and restoring near-BF16 performance across GRPO and DAPO, 8B to 32B models, and multiple FP8 scaling granularities, while reaching up to 1.5x the BF16 training throughput.
You’re all caught up