tool-calling

Ollama released v0.32.1 on July 16, 2024, addressing a critical MLX model cache memory leak that increased memory usage across requests. The update also improves Gemma 4 tool calling reliability and adds authentication prompts for agent web search features.

Meta has released Muse Spark 1.1, the first model in the Spark series to offer API access. The company claims significant improvements in agentic tool calling and computer use compared to the original Muse Spark released in April 2026.

Amazon Bedrock now supports programmatic tool calling (PTC), a technique that allows LLMs to generate Python code for multi-step tool orchestration rather than making sequential API calls. AWS offers three implementation paths: self-hosted Docker sandboxes on ECS, managed execution via Amazon Bedrock AgentCore Code Interpreter, and Anthropic SDK-compatible proxy integration.

IBM released Granite 4.1 30B, a 30-billion parameter instruction-following model with a 131,072 token context window. The model scores 80.16 on MMLU 5-shot and 88.41 on HumanEval pass@1, with enhanced tool-calling capabilities following OpenAI's function definition schema.

IBM has released Granite 4.1-8B, an 8-billion parameter long-context model with a 131,072-token context window. The model achieves 85.37% on HumanEval and 73.84% on MMLU 5-shot, with enhanced tool-calling capabilities reaching 68.27% on BFCL v3. Released under Apache 2.0 license, it supports 12 languages.

Arcee AI released Trinity-Large-Thinking, a 398B-parameter sparse Mixture-of-Experts model with approximately 13B active parameters per token, post-trained with extended chain-of-thought reasoning for agentic workflows. The model achieves 94.7% on τ²-Bench, 91.9% on PinchBench, and 98.2% on LiveCodeBench, generating explicit reasoning traces in <think>...</think> blocks before producing responses.

LocoreMind has released LocoOperator-4B, a 4 billion parameter text generation model fine-tuned from Qwen/Qwen3-4B-Instruct-2507. The model is optimized for agent workflows and tool-calling capabilities and is available under an MIT license.