SchemaFill: Efficient LLM Tool Calling via Slot-Parallel Speculative Decoding

arXiv:2610.07086 · cs.LG, cs.AI · Submitted 2026-10-05 · Read on arXiv

cs.LG, cs.AI

Submitted: 2026-10-05

Updated: 2026-10-05

Code: https://github.com/Czzzk/SchemaFill

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Speculative Decoding — 1× in this paper · explained in 2 episodes

Sources

• Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads
• Accelerating Large Language Model Decoding with Speculative Sampling
• Hawk: Leveraging Spatial Context for Faster Autoregressive Text-to-Image Generation
• ResiSpec: Enhancing Multi-Candidate Speculative Sampling via Residual Distribution Shaping
• PeakBench: Benchmarking Resource-Aware Tool Invocation in LLM Agents
• JSONSchemaBench: A Rigorous Benchmark of Structured Outputs for Language Models
• Mistral 7B
• EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty
• ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases
• Efficient Guided Generation for Large Language Models
• ToolSpec: Accelerating Tool Calling via Schema-Aware and Retrieval-Augmented Speculative Decoding
• Qwen2.5 Technical Report
• Qwen3 Technical Report
• ReAct: Synergizing Reasoning and Acting in Language Models

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks