AIarXiv
Ranked by formulaVerdict: NotableToolSpace: Scaling Tool-Centric Environment Synthesis for Long-Horizon Agents
Large language models are deployed as long-horizon agents that compose diverse tools across MCP services into executable workflows.
Caveats
- Preprint; not yet peer reviewed.
VerdictWorth a reader's time today.
Abstract
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 clusters the resulting weighted tool-composition graph into environments. Databases are synthesized only for state-mutating environments, while query and stateless tools replay recorded returns. ToolSpace then performs state-aware random walks with rollback and decompiles each chain into a natural-language task with assertion-based checks, keeping only samples that replay successfully from the initial state. Applied to AutomationBench and tau3-Bench Banking, the pipeline produces harder Pro versions on which 7 frontier models drop by up to 38.2 points. Across seven long-horizon tool-use benchmarks, ToolSpace raises Qwen3.6-35B-A3B from 23.0 to 41.0 average score (43.2 with RL) and GLM-5.2 from 44.6 to 56.6, on par with Claude Opus 5. Ablations show that execution-witnessed edges clearly outperform LLM-judged ones, and performance keeps improving with data and environment scale.
The editor's rubric
- Leverage3 / 5
- A method or resource many groups across the field will adopt within a year.
- Magnitude3 / 5
- Large gain: roughly 2x, or a clear new state of the art on a hard, unsaturated problem.
- Evidence3 / 5
- Solid: multiple benchmarks or cohorts, ablations, fair baselines, released code or data.
- Novelty3 / 5
- A genuinely new approach to an open problem.
- Trajectory3 / 5
- A clear path to scale.
- Stakes2 / 5
- Benefits a professional community (practitioners, clinicians, engineers).
Editor’s rationale
Heuristic triage from title and abstract text only, not a reading of the paper. Cues found: method (we propose); gains (outperforms); novelty (alternative to status quo); verification (multiple benchmarks, ablations); scale (scalable, improves with scale); stakes (general AI).
How the score was computed
Desks place stronger verdicts first, then use this score to order work within the same verdict.
- Merit
- 5.8 / 10
- Adjusted merit
- 4.8 / 10
- Attention
- 65%
- Freshness
- 77%
- Hugging Face upvotes31 (reference 25, via hf-daily, Nov 4, 2026, 13:49 UTC)
- GitHub stars7 (reference 250, via hf-daily, Nov 4, 2026, 13:49 UTC)