{"slug": "memory-conditioned-tool-calling-for-camera-first-visual-agents", "title": "Memory-Conditioned Tool Calling for Camera-First Visual Agents", "summary": "Researchers introduced a memory-conditioned tool-calling system for camera-first visual agents that uses a three-layer personal visual memory to improve tool selection and argument generation. In tests on 800 images, removing the memory block reduced tool-query relevance by 11.2% and end-to-end utility by 9.7%, demonstrating the importance of personal memory for user-aligned multi-tool lookups.", "body_md": "arXiv:2607.09822v1 Announce Type: new\nAbstract: Recognition tells an agent what is in an image; personal memory affects what is worth looking up next. In a camera-first setting the user can send only an image, so the agent must form the lookups. We study whether personal visual memory improves agent-side tool choice and tool arguments, and thereby more user-aligned multi-tool lookups. The design uses a three-layer personal visual memory (profile, short-term focus, observations) that is loaded on each turn to condition an LLM tool-calling loop under camera-first intake, and includes conflict-aware write-back intended to refresh the user model for later captures. On 800 images paired with synthetic memory blocks constructed for controlled ablation, removing the full three-layer memory block reduces tool-query relevance by 0.47 points absolute (4.21 -> 3.74 on a 5-point scale; 11.2% relative) and end-to-end utility by 0.082 absolute (0.842 -> 0.760; 9.7% relative). These results measure memory conditioning of tool policy under image-only intake with fixed synthetic blocks, not multi-session write-back from live user histories.", "url": "https://wpnews.pro/news/memory-conditioned-tool-calling-for-camera-first-visual-agents", "canonical_source": "https://arxiv.org/abs/2607.09822", "published_at": "2026-07-14 04:00:00+00:00", "updated_at": "2026-07-14 04:04:04.045669+00:00", "lang": "en", "topics": ["artificial-intelligence", "computer-vision", "large-language-models", "ai-agents", "ai-research"], "entities": [], "alternates": {"html": "https://wpnews.pro/news/memory-conditioned-tool-calling-for-camera-first-visual-agents", "markdown": "https://wpnews.pro/news/memory-conditioned-tool-calling-for-camera-first-visual-agents.md", "text": "https://wpnews.pro/news/memory-conditioned-tool-calling-for-camera-first-visual-agents.txt", "jsonld": "https://wpnews.pro/news/memory-conditioned-tool-calling-for-camera-first-visual-agents.jsonld"}}