New training and agent strategies aim to cut token usage by reasoning internally, reconstructing reasoning traces offline, or producing fewer tokens at equal quality. This reduces cost and latency while maintaining benchmark performance.
Migtissera has released a GGUF fine-tune of a Qwen model. Internal benchmarks suggest it produces up to a quarter fewer tokens for the same score. Fewer tokens mean faster responses, longer sessions and lower inference costs—an advantage for teams ru...
Reflection has released Beam, an open LLM with a 501-billion total and 23-billion active parameter MoE architecture. It supports a 1 million token context and BF16, FP8, and NVFP4 precision. The focus is token-efficient reasoning: about one third of ...
A preprint from Stanford, Together AI, UIUC, and Meta introduces Hybrid Reasoning Agents: models that reason internally and emit text only for tool use and final answers. In reported tests they gain about 10%, use half the tokens, run twice as fast, ...
Researchers use an inverse LLM to reconstruct reasoning traces from answers alone. Trained once, the model generates intermediate steps offline for prompt-answer data, avoiding the multiple rollouts of reinforcement learning. On Qwen3-0.6B, a single ...
