Hexo Labs released SIA, an open-source self-improving loop, under an MIT license. A Feedback-Agent reads each run's trajectory, then either rewrites the scaffold or triggers a LoRA weight update on gpt-oss-120b. Combining both levers beat scaffold-only iteration on LawBench, TriMul GPU kernels, and scRNA-seq denoising.
The post Hexo Labs Open-Sources SIA: A Self-Improving Agent That Updates Both the Harness and the Model Weights appeared first on MarkTechPost.
DeepReinforce released Ornith-1.0, an open-source coding model family built on Gemma 4 and Qwen 3.5. Instead of a fixed harness, the model learns its own scaffold during reinforcement learning. The 397B flagship reports 82.4 on SWE-Bench Verified, with all weights under the MIT license.
The post DeepReinforce Releases Ornith-1.0: An Open-Source Coding Model Family That Learns Its Own RL Scaffolds appeared first on MarkTechPost.
Insider Brief One of artificial intelligence’s longest-running challenges is building systems that can improve both how they operate and what they know without requiring constant human intervention. A research team now reports that a new approach could shatter that bottleneck. In a study published on the preprint server arXiv, researchers at Palo Alto-based Hexo Labs […]
Tencent has open-sourced TencentDB Agent Memory, a fully local memory system for AI agents released under the MIT license. The project pairs symbolic short-term memory, which offloads verbose tool logs into a compact Mermaid task canvas, with a 4-tier long-term memory pyramid (L0 Conversation → L1 Atom → L2 Scenario → L3 Persona). It ships as an OpenClaw plugin and a Hermes Docker image, runs on local SQLite + sqlite-vec by default, and uses hybrid BM25 + vector retrieval with RRF fusion. Tencent's own benchmarks report a 61.38% token reduction and 51.52% relative pass-rate gain on WideSearch with OpenClaw, alongside PersonaMem accuracy moving from 48% to 76%.
The post Tencent Open-Sources TencentDB Agent Memory: A 4-Tier Local Memory Pipeline for AI Agents appeared first on MarkTechPost.
Xiaomi has released and open-sourced MiMo-V2.5 and MiMo-V2.5-Pro under the MIT License, giving developers another potentially lower-cost option for building AI agents that can run longer tasks such as coding and workflow automation.
Both models support a 1-million-token context window, the company said. MiMo-V2.5-Pro is designed for complex agent and coding tasks, while MiMo-V2.5 is a native omnimodal model that supports text, images, video, and audio.
The release comes as agentic AI workloads are putting new pressure on enterprise AI budgets. These systems can burn through large numbers of tokens as they plan, call tools, write code, and recover from errors, making cost and deployment control increasingly important for developers.
By using the MIT License, Xiaomi said it is allowing commercial deployment, continued training, and fine-tuning without additional authorization. Tulika Sheel, senior vice president at Kadence International, said the MIT License can make it attractive. “It a
Xiaomi has released and open-sourced MiMo-V2.5 and MiMo-V2.5-Pro under the MIT License, giving developers another potentially lower-cost option for building AI agents that can run longer tasks such as coding and workflow automation.
Both models support a 1-million-token context window, the company said. MiMo-V2.5-Pro is designed for complex agent and coding tasks, while MiMo-V2.5 is a native omnimodal model that can work with text, images, video, and audio.
The release comes as agentic AI workloads are putting new pressure on enterprise AI budgets. These systems can burn through large numbers of tokens as they plan, call tools, write code, and recover from errors, making cost and deployment control increasingly important for developers.
By using the MIT License, Xiaomi said it is allowing commercial deployment, continued training, and fine-tuning without additional authorization. Tulika Sheel, senior vice president at Kadence International, said the MIT License can make it attractive.
