News without the noise
Tool ecosystems, MCP, function calling
8 articles
The authors replace conventional generate-then-filter data synthesis with a loop that generates, verifies, and refines examples at multiple stages. A 4B-parameter model trained on 11K ToolLoop examples reached 86.40% accuracy on the Berkeley Function Calling Leaderboard and generalized to ACEBench with substantially less training data than the cited baseline.
10 Sept 2026Xie and Chen replace visual GUI control with an agent-facing layer that represents application state as JSON and exposes semantically meaningful, code-executable actions. On 380 single- and multi-application tasks, closed models using ASIL achieved more than 80% strict success while averaging fewer than five actions per task, far exceeding screenshot-based control under the tested conditions.
29 Aug 2026Zhang et al. developed a video question-answering agent that combines video understanding with external retrieval while adapting its tools to each task. Trained with supervised fine-tuning and reinforcement learning, AdaVDR led the evaluated open-source models on the authors’ VDR-EE benchmark and improved substantially over its base models on VideoDR.
28 Aug 2026Tam et al. jointly trained a 4-billion-parameter Qwen3 model on tool creation and tool use across 13 procedural reasoning tasks. The resulting model achieved 79.8% macro-average accuracy on held-out tasks and transferred to tabular and visual question answering without training on either data type.
27 Aug 2026The authors introduce Boogu-Image-0.1, a family of open-source multimodal models that unify understanding and generation. By strengthening the system's understanding capability through a better multimodal encoder, agentic prompt rewriting, and inference-time scaling, the model matches or surpasses existing open-source models and approaches closed-source systems, all with a theoretical training cost of roughly $400K.
15 July 2026The authors present CRAFT, a two-stage post-training recipe that enables enterprise coding agents to learn schema and tool-use behavior without exhaustive prompt-time schema injection. They show that CRAFT improves composite Agent Score by +9.6 percentage points, reduces input tokens by ~9x, and cuts schema-discovery loops by up to 5x compared to a schema-stuffed baseline.
24 June 2026The authors present IEA, a conversational image editing agent that manipulates 16 parameterized tools step by step instead of generating pixels directly. Trained via a three-stage multitask pipeline, IEA achieves lower pixel distance on editing tasks and higher ROUGE-L on intent summaries than strong baselines, and outperforms both tool-calling and generative methods in user studies.
6 June 2026The authors propose Astra, an agentic spatial reasoning framework that combines two components: a world simulator (Astra-WM) that generates novel-view images from context images and natural-language camera motions, and an RL-trained VLM policy (Astra-VL) that decides when to query the simulator. Trained with view consistency tuning and a two-phase RL curriculum, Astra improves spatial reasoning benchmarks by 9–10 points over direct VLM answering, demonstrating that effective world-model-augmented reasoning requires learning when, where, and how to imagine.
5 June 2026