paper-with-me

Papers

ToolRLA: Multiplicative Reward Decomposition for Tool-Integrated Agents

2026-03-02 · Pengbo Liu 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.

📄 PDF Abstract BibTeX arXiv:2603.01620

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Value Function Decomposition for Iterative Design of Reinforcement Learning Agents

2022-06-24 · James Macglashan, Evan Archer, Alisa Devlic, Takuma Seno 외

Designing reinforcement learning (RL) agents is typically a difficult process that requires numerous design iterations. Learning can fail for a multitude of reasons, and standard RL methods provide too few tools to provi…

Decision Makingreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Multiplicative Decomposition of Heterogeneity in Mixtures of Continuous Distributions

2020-06-17

A system's heterogeneity (\textit{diversity}) is the effective size of its event space, and can be quantified using the R\'enyi family of indices (also known as Hill numbers in ecology or Hannah-Kay indices in economics)…

Rethinking Reinforcement Fine-Tuning in LVLM: Convergence, Reward Decomposition, and Generalization

2026-04-21 · Carter Adams, Rafael Oliveira, Gabriel Almeida, Sofia Torres arxiv

Reinforcement fine-tuning with verifiable rewards (RLVR) has emerged as a powerful paradigm for equipping large vision-language models (LVLMs) with agentic capabilities such as tool use and multi-step reasoning. Despite …

Orbital-Angular-Momentum Embedded Massive MIMO: Achieving Multiplicative Spectrum-Efficiency for mmWave Communications

2024-08-13 · Wenchi Cheng, Hailin Zhang, Liping Liang, Haiyue Jing 외

By enabling very high bandwidth for radio communications, the millimeter-wave (mmWave), which can easily be integrated with massive-multiple-input-multiple-output (massive-MIMO) due to small antenna size, has been attrac…

Agent0-VL: Exploring Self-Evolving Agent for Tool-Integrated Vision-Language Reasoning

2025-11-25 · Jiaqi Liu, Kaiwen Xiong, Peng Xia, Yiyang Zhou 외 arxiv

Vision-language agents have achieved remarkable progress in a variety of multimodal reasoning tasks; however, their learning remains constrained by the limitations of human-annotated supervision. Recent self-rewarding ap…

Reinforcement LearningMultimodal ReasoningVisual Reasoning