Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

CacheRL:Multi-Turn Tool-Calling Agents via Cached Rollouts and Hybrid Reward

About

We present CacheRL, a system for training small agent foundation models that achieves 92 percent process accuracy on multi-step tool-calling tasks, approaching GPT-5's 94 percent while requiring 100 times less compute. Our approach addresses three challenges in practical agent training: transferring tool-calling knowledge from large models at scale, enabling reinforcement learning without costly live tool execution, and learning robustly from noisy cached environments. CacheRL introduces three key innovations. First, a hybrid thinking trajectory pipeline augments agent trajectories with LLM-generated reasoning traces, producing training examples that teach models not only what tools to call but also why. Second, the CacheAgentLoop eliminates live execution costs through a three-tier fuzzy cache while preserving trajectory fidelity using token-level masking. Third, a cache-tier-aware reward dynamically adjusts answer-quality weights to avoid penalizing models for cache-induced limitations. Through iterative supervised fine-tuning (SFT) and Group Relative Policy Optimization (GRPO), CacheRL improves Qwen3-4B-Thinking's validation reward from 0.43 to 0.78. On public agentic tool-calling benchmarks, our model achieves competitive performance against frontier models such as GPT-5. Ablation studies show that removing knowledge transfer reduces performance by 41 percent, while cache-aware rewards contribute a 17 percent improvement. Interestingly, reinforcement learning improves training stability but yields limited gains beyond strong supervised fine-tuning, suggesting that data quality and reward design play a more important role than complex optimization methods in building practical small agent models.

Md Amirul Islam, Sumiran Thakur, Huancheng Chen, Su Min Park, Jiayun Wang, Gyuhak Kim• 2026

Related benchmarks

TaskDatasetResultRank
Key-value recallMemory KV 37 cases (test)
Accuracy29
7
Recursive summarizationMemory Rec Sum 13 tasks
Accuracy0.7692
7
Multi-step tool-callingACEBench
End-to-End Success Rate0.8
6
Multi-Turn Tool CallingACEBench
End-to-End Success Rate9
6
Showing 4 of 4 rows

Other info

Follow for update