Fetching from the wire…
01
02
03
04
05
06
07
08
Agents2026-08-29 · source-backed
MoRe learns a codebook of steering vectors, each encoding a latent role, then uses a query-aware router to fuse them into a single composed vector for single-turn inference. The backbone stays frozen; training is a three-stage SFT curriculum plus GRPO. Across reasoning and personality benchmarks it beats single-agent baselines by 2.2% on average and matches multi-agent systems at a twentieth of the tokens. If your reason for running a multi-agent pipeline is role diversity rather than parallelism or tool isolation, this is a direct argument you're paying 20x for something a steering vector does. (arXiv)
Each link below shares sources, entities, or timing with this story.
New batching algorithms enable ~7x, up to 12x+, longer-context GRPO training with no accuracy or speed penalty versus optimized FA3 and chunked-loss setups (Unsloth Docs). Qwen3-8B GRPO reaches 110K context on one 80GB H100 via vLLM plus QLoRA. For solo builders doing reasonin...
Two specialized RL agents — Memory Manager (ADD/UPDATE/DELETE operations) and Answer Agent — fine-tuned with PPO and GRPO. With only 152 training QA pairs, outperforms baselines across three benchmarks. Directly applicable to persistent agent memory systems. arXiv 2508.19828
Rather than a separate router model, PyroDash internalizes the escalation policy inside the small model: mid-generation the SLM emits a control token, and a Collaborate Engine hands the query plus partial reasoning trace to a frozen LLM for a single completion. No LLM retraini...
Google DeepMind released Gemma 4 on April 2 with four model sizes (E2B, E4B, 26B MoE, 31B Dense) under Apache 2.0. Multimodal (text, vision, audio). 256K context. Native thinking and tool-calling optimized for agentic workflows. Day-zero ecosystem support across vLLM, llama.cp...
Alibaba released Qwen3.6-27B on April 22. Dense architecture. Open weights. 77.2% on SWE-bench Verified, within 3.7 points of Claude Opus 4.6. On SkillsBench, it scores 48.2% versus its own 397B MoE predecessor's 30.0%. That's a 77% improvement with 14.8x fewer parameters. Let...
AxisAgentic (855 stars) is a runtime emitting append-only traces that reconstruct exactly what the model observed at any point, with explicit runtime markers for rollback, context compaction and discard events: which is what makes state-faithful SFT export possible without lea...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.