Large language models are deployed as long-horizon agents that compose diverse tools across MCP services into executable workflows. Existing MCP environment-scaling methods are data-centric: they firs
ToolSpace constructs realistic multi-environment tool-use benchmarks by mining execution traces, clustering tool compositions, and validating tasks through replayable state-aware random walks.
Large language models are deployed as long-horizon agents that compose diverse tools across MCP services into executable workflows. Existing MCP environment-scaling methods are data-centric: they first synthesize a database and scenario, then derive tools and tasks from them. As a result, tool interfaces may not match real ones, tool compositions are not grounded in execution, and tasks rarely span more than one environment. We propose ToolSpace, a tool-centric framework that reverses this order. ToolSpace mines data, state, and retry dependencies from adjacent calls in execution traces of real MCP services and open agent corpora, using deterministic rules rather than LLM judgment, and…
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.
ToolSpace: Scaling Tool-Centric Environment Synthesis for Long-Horizon Agents was first seen on Hugging Face · Daily papers on Nov 4, 2026. Since then it has appeared in 13 checks on 2 different days. Its best position was #5 of 30, reached on Nov 5, 07:28 UTC. It dropped off the list after Nov 5, 07:28 UTC.
Position on Hugging Face · Daily papers at every check (lower is better).
Best rank per day (UTC).
Platform metric as reported by Hugging Face.
Archived daily, weekly and monthly lists that include this entry.
Not at the moment. It was last on the list on Nov 5, 07:28 UTC, after 2 days of trending.
#5 on Hugging Face · Daily papers, on Nov 5, 07:28 UTC. Trendoday checks this list every 120 minutes.
It was first seen on Nov 4, 2026 and has been on the list on 2 days (13 checks) since.