# Process-Supervised Reinforcement Learning for Interactive Multimodal Tool-Use Agents

arXiv: https://arxiv.org/abs/2509.14480 · HTML: https://mlsanity.com/paper/2509.14480/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for LLM agents, one of 16 directions in LLM agents and tool use.
- Builds on 17 of its 36 references that are in the map.
- First posted on arXiv 17 Sep 2025.

## Placed in

- LLM agents and tool use / [Reinforcement learning for LLM agents](https://mlsanity.com/agents/reinforcement-learning-for-llm-agents/)

## Builds on (most cited first, 17 of 17)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents](https://mlsanity.com/paper/2207.01206/) (2022)
- [Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?](https://mlsanity.com/paper/2504.13837/) (2025)
- [τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environment](https://mlsanity.com/paper/2506.07982/) (2025)
- [Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning](https://mlsanity.com/paper/2506.01939/) (2025)
- [The Lessons of Developing Process Reward Models in Mathematical Reasoning](https://mlsanity.com/paper/2501.07301/) (2025)
- [Seed-TTS: A Family of High-Quality Versatile Speech Generation Models](https://mlsanity.com/paper/2406.02430/) (2024)
- [APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay](https://mlsanity.com/paper/2504.03601/) (2025)
- [Beyond Binary Rewards: Training LMs to Reason About Their Uncertainty](https://mlsanity.com/paper/2507.16806/) (2025)
- [Let's reward step by step: Step-Level reward model as the Navigators for Reasoning](https://mlsanity.com/paper/2310.10080/) (2023)
- [Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Models](https://mlsanity.com/paper/2503.02318/) (2025)
- [Process Reward Models for LLM Agents: Practical Framework and Directions](https://mlsanity.com/paper/2502.10325/) (2025)

## Built on by (most cited first, 12 of 12)

- [From Reasoning to Agentic: Credit Assignment in Reinforcement Learning for Large Language Models](https://mlsanity.com/paper/2604.09459/) (2026)
- [VoiceAgentBench: Are Voice Assistants ready for agentic tasks?](https://mlsanity.com/paper/2510.07978/) (2025)
- [Klear-AgentForge: Forging Agentic Intelligence through Posttraining Scaling](https://mlsanity.com/paper/2511.05951/) (2025)
- [OASES: Outcome-Aligned Search-Evaluation Co-Training for Agentic Search](https://mlsanity.com/paper/2604.03675/) (2026)
- [Why Multi-Step Tool-Use Reinforcement Learning Collapses and How Supervisory Signals Fix It](https://mlsanity.com/paper/2606.26027/) (2026)
- [Credit Without Ground Truth: Auditing Step-Level Credit Assignment in LLM Agents Against Executed Replay](https://mlsanity.com/paper/2608.19760/) (2026)
- [Harmonizing Dense and Sparse Signals in Multi-turn RL: Dual-Horizon Credit Assignment for Industrial Sales Agents](https://mlsanity.com/paper/2603.01481/) (2026)
- [AgentCVR: Active Multi-Agent Cross-Video Reasoning via Script-Simulated Reinforcement Learning](https://mlsanity.com/paper/2605.29643/) (2026)
- [CAST: Critique-Aware Supervision for Training Reliable Long-Horizon Tool-Calling Agents](https://mlsanity.com/paper/2608.30147/) (2026)
- [From Correctness to Preference: A Framework for Personalized Agentic Reinforcement Learning](https://mlsanity.com/paper/2605.23382/) (2026)
- [CityPlanner: A Sandbox Agent for Executable Urban Planning](https://mlsanity.com/paper/2609.09578/) (2026)
- [Of Errors and Echoes: Responsibility-Aware Credit Assignment for Tool-Use Agents](https://mlsanity.com/paper/2610.16027/) (2026)

## Abstract (arXiv)

Effective interactive tool use requires agents to master Tool Integrated Reasoning (TIR): a complex process involving multi-turn planning and long-context dialogue management. To train agents for this dynamic process, particularly in multi-modal contexts, we introduce a sandbox environment for reinforcement learning (RL) that supports interleaved speech-text rollouts. Our core strategy, Turn-level Adjudicated Reinforcement Learning (TARL), addresses the challenge of credit assignment in long-horizon tasks by employing a Large Language Model (LLM) as a judge to provide turn-level evaluation. To enhance exploration, we integrate a mixed-task training curriculum with mathematical reasoning problems. This unified approach boosts the task pass rate on the text-based τ-bench by over 6% compared to strong RL baselines. Crucially, we demonstrate our framework's suitability for fine-tuning a multi-modal foundation model for agentic tasks. By training a base multi-modal LLM on interleaved speech-text rollouts, we equip it with tool-use abilities, paving the way for more natural, voice-driven interactive agents.