{"slug": "tracer-trajectory-aware-tool-retrieval-for-llm-agents", "title": "TRACER: Trajectory-Aware Tool Retrieval for LLM Agents", "summary": "TRACER, a retrieval front-end that indexes observed tool-call sequences in a trie and ranks continuations using a learned blend of empirical and contextual priors, improved GPT-5.4's tool-selection accuracy by 4.7 points on a mixed retail-and-telecom τ² environment while cutting input tokens per step by 80% and exposing just 5 of 128 tools, according to the arXiv paper 2610.21267v1. In autonomous full-turn execution, TRACER matched GPT-5.4's full-registry task success with 61% fewer input tokens per step, and across six environments and four models it improved tool-selection accuracy over full-registry selection in 21 of 24 model-environment pairs, with average gains of 6 to 10 points and the three exceptions trailing by at most 2.2 points.", "body_md": "arXiv:2610.21267v1 Announce Type: new \nAbstract: Modern agents select tools from registries, but exposing entire registries incurs high token costs and can impair selection as they grow. We present TRACER, a retrieval front-end that indexes observed tool-call sequences in a trie and ranks continuations using a learned blend of empirical and contextual priors. On a mixed retail-and-telecom $\\tau^2$ environment, TRACER improves GPT-5.4's tool-selection accuracy by 4.7 points while reducing input tokens per step by 80%, exposing just 5 of 128 tools. In autonomous full-turn execution, it matches GPT-5.4's full-registry task success with 61% fewer input tokens per step. Across six environments and four models, TRACER improves tool-selection accuracy over full-registry selection in 21 of 24 model-environment pairs, with average gains of 6 to 10 points; the three exceptions trail by at most 2.2. We analyze failures in both regimes to identify directions for future work.", "url": "https://wpnews.pro/news/tracer-trajectory-aware-tool-retrieval-for-llm-agents", "canonical_source": "https://www.machinebrief.com/news/tracer-trajectory-aware-tool-retrieval-for-llm-agents-x200", "published_at": "2026-10-16 04:00:00+00:00", "updated_at": "2026-10-16 05:36:26.998889+00:00", "lang": "en", "topics": ["ai-agents", "ai-tools", "large-language-models", "ai-research", "natural-language-processing"], "entities": ["TRACER", "GPT-5.4", "arXiv"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/tracer-trajectory-aware-tool-retrieval-for-llm-agents", "markdown": "https://wpnews.pro/news/tracer-trajectory-aware-tool-retrieval-for-llm-agents.md", "text": "https://wpnews.pro/news/tracer-trajectory-aware-tool-retrieval-for-llm-agents.txt", "jsonld": "https://wpnews.pro/news/tracer-trajectory-aware-tool-retrieval-for-llm-agents.jsonld"}}