mlsanityData to 7 Oct 2026

ToolRLA: Multiplicative Reward Decomposition for Tool-Integrated Agents

arXiv 2603.01620 ↗First posted 2 Mar 2026cs.AIcited by 1

On the map: LLM agents and tool use → Reinforcement learning for LLM agents

also in 1 more
Abstract (arXiv)

Tool-integrated agents that interleave reasoning with API calls are promising for complex tasks, yet aligning them for high-stakes, domain-specific deployment remains challenging: existing reinforcement learning approaches rely on coarse binary rewards that cannot distinguish tool selection errors from malformed parameters. We present ToolRLA, a three-stage post-training pipeline (SFT -> GRPO -> DPO) for domain-specific tool agents. The core contribution is a fine-grained reward function with multiplicative correctness decomposition spanning four dimensions -- format validity, tool selection, parameter accuracy, and regulatory compliance -- that encodes domain priority orderings as inductive biases in the reward landscape. Deployed on a financial advisory copilot (80+ advisors, 1,200+ daily queries), ToolRLA achieves over three months: a 47% improvement in task completion rate (62%->91%), a 63% reduction in tool invocation errors (38%->14%), and a 93% reduction in regulatory violations (12%->0.8%), within sub-2-second latency. Ablation studies show the multiplicative reward design accounts for 7 percentage points of improvement over additive alternatives. Generalization is further validated on ToolBench and API-Bank.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Reinforcement learning for LLM agents, one of 16 directions in LLM agents and tool use. Builds on 12 of its 18 references that are in the map. First posted on arXiv 2 Mar 2026.

Builds on

12 of 18 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025Group-in-Group Policy Optimization for LLM Agent Training16 May
  2. 2025ReTool: Reinforcement Learning for Strategic Tool Use in LLMs15 Apr

Other references · 10

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  4. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  5. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  6. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,880
  7. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,302
  8. 2023API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMscited by 574
  9. 2024AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Callscited by 121
  10. 2024AvaTaR: Optimizing LLM Agents for Tool Usage via Contrastive Reasoningcited by 69

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026The Workload-Router-Pool Architecture for LLM Inference Optimization: A Vision Paper from the vLLM Semantic Router Projectcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025PORTool: Importance-Aware Policy Optimization with Rewarded Tree for Multi-Tool-Integrated Reasoning
  2. 2026Controllable and Verifiable Tool-Use Data Synthesis for Agentic Reinforcement Learning
  3. 2025ToolBrain: A Flexible Reinforcement Learning Framework for Agentic Tools
  4. 2026Reasoning and Tool-use Compete in Agentic RL:From Quantifying Interference to Disentangled Tuning
  5. 2025ToolRL: Reward is All Tool Learning Needs
  6. 2026CM2: Reinforcement Learning with Checklist Rewards for Multi-Turn and Multi-Step Agentic Tool Use
  7. 2025AutoTIR: Autonomous Tools Integrated Reasoning via Reinforcement Learning
  8. 2026AdaTIR: Adaptive Tool-Integrated Reasoning via Difficulty-Aware Policy Optimization