# Agentic Reinforcement Learning with Implicit Step Rewards

arXiv: https://arxiv.org/abs/2509.19199 · HTML: https://mlsanity.com/paper/2509.19199/

## Key facts

- Cited by 47 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 38 of its 46 references that are in the map.
- First posted on arXiv 23 Sep 2025.

## Placed in

- LLM agents and tool use / [Reinforcement learning for LLM agents](https://mlsanity.com/agents/reinforcement-learning-for-llm-agents/)
- LLM alignment / RLHF / preference optimisation / [Process reward models for reasoning](https://mlsanity.com/alignment/process-reward-models-for-reasoning/)

## Builds on (most cited first, 30 of 38)

- [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)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents](https://mlsanity.com/paper/2207.01206/) (2022)
- [Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations](https://mlsanity.com/paper/2312.08935/) (2023)
- [Group Sequence Policy Optimization](https://mlsanity.com/paper/2507.18071/) (2025)
- [Process Reinforcement through Implicit Rewards](https://mlsanity.com/paper/2502.01456/) (2025)
- [Group-in-Group Policy Optimization for LLM Agent Training](https://mlsanity.com/paper/2505.10978/) (2025)
- [RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning](https://mlsanity.com/paper/2504.20073/) (2025)
- [SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents](https://mlsanity.com/paper/2310.11667/) (2023)
- [Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning](https://mlsanity.com/paper/2410.08146/) (2024)
- [SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution](https://mlsanity.com/paper/2502.18449/) (2025)
- [From r to Q^*: Your Language Model is Secretly a Q-Function](https://mlsanity.com/paper/2404.12358/) (2024)
- [Self-Play Preference Optimization for Language Model Alignment](https://mlsanity.com/paper/2405.00675/) (2024)
- [DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning](https://mlsanity.com/paper/2406.11896/) (2024)
- [VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learning](https://mlsanity.com/paper/2505.18719/) (2025)
- [Free Process Rewards without Process Labels](https://mlsanity.com/paper/2412.01981/) (2024)
- [WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning](https://mlsanity.com/paper/2505.16421/) (2025)
- [Multimodal Web Navigation with Instruction-Finetuned Foundation Models](https://mlsanity.com/paper/2305.11854/) (2023)
- [Generative Reward Models](https://mlsanity.com/paper/2410.12832/) (2024)

## Built on by (most cited first, 30 of 47)

- [Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation](https://mlsanity.com/paper/2602.12125/) (2026)
- [Hindsight Credit Assignment for Long-Horizon LLM Agents](https://mlsanity.com/paper/2603.08754/) (2026)
- [From Reasoning to Agentic: Credit Assignment in Reinforcement Learning for Large Language Models](https://mlsanity.com/paper/2604.09459/) (2026)
- [HiPER: Hierarchical Reinforcement Learning with Explicit Credit Assignment for Large Language Model Agents](https://mlsanity.com/paper/2602.16165/) (2026)
- [Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Tasks](https://mlsanity.com/paper/2604.20987/) (2026)
- [RTMC: Step-Level Credit Assignment via Rollout Trees](https://mlsanity.com/paper/2604.11037/) (2026)
- [Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning](https://mlsanity.com/paper/2509.22601/) (2025)
- [RC-GRPO: Reward-Conditioned Group Relative Policy Optimization for Multi-Turn Tool Calling Agents](https://mlsanity.com/paper/2602.03025/) (2026)
- [FlowSteer: Towards Agents Designing Agentic Workflows via Reinforced Progressive Canvas Editing](https://mlsanity.com/paper/2602.01664/) (2026)
- [GAGPO: Generalized Advantage Grouped Policy Optimization](https://mlsanity.com/paper/2605.13217/) (2026)
- [Search-E1: Self-Distillation Drives Self-Evolution in Search-Augmented Reasoning](https://mlsanity.com/paper/2605.22511/) (2026)
- [Socratic-SWE: Self-Evolving Coding Agents via Trace-Derived Agent Skills](https://mlsanity.com/paper/2606.07412/) (2026)
- [Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks](https://mlsanity.com/paper/2607.22724/) (2026)
- [CAPO: Critic-Guided Action-Aligned Policy Optimization for Advancing LLM Agent Capabilities](https://mlsanity.com/paper/2604.18401/) (2026)
- [BiPACE: Bisimulation-Guided Policy Optimization with Action Counterfactual Estimation for LLM Agents](https://mlsanity.com/paper/2606.25556/) (2026)
- [SkillFlow: Flow-Driven Recursive Skill Evolution for Agentic Orchestration](https://mlsanity.com/paper/2605.14089/) (2026)
- [Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents](https://mlsanity.com/paper/2606.26080/) (2026)
- [Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis](https://mlsanity.com/paper/2604.24198/) (2026)
- [Resolving Action Bottleneck: Agentic Reinforcement Learning Informed by Token-Level Energy](https://mlsanity.com/paper/2605.14558/) (2026)
- [TikArt: Stabilizing Aperture-Guided Fine-Grained Visual Reasoning with Reinforcement Learning](https://mlsanity.com/paper/2602.14482/) (2026)
- [StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction](https://mlsanity.com/paper/2605.06642/) (2026)
- [ARCO: Adaptive Rubrics with Co-Evolution for Multi-Step LLM-Based Agents](https://mlsanity.com/paper/2606.21262/) (2026)
- [RewardFlow: Topology-Aware Reward Propagation on State Graphs for Agentic RL with Large Language Models](https://mlsanity.com/paper/2603.18859/) (2026)
- [TRACE: Capability-Targeted Agentic Training](https://mlsanity.com/paper/2604.05336/) (2026)
- [Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents](https://mlsanity.com/paper/2605.20061/) (2026)
- [Hierarchical Reinforcement Learning with Augmented Step-Level Transitions for LLM Agents](https://mlsanity.com/paper/2604.05808/) (2026)
- [RLVP: Penalize the Path, Reward the Outcome](https://mlsanity.com/paper/2607.07435/) (2026)
- [Process Reward Informed Tree Rollout for Effective Multi-Turn RL](https://mlsanity.com/paper/2607.15610/) (2026)
- [CoRT: Counterfactual Replay for Token-Level Rubric-Guided Policy Optimization](https://mlsanity.com/paper/2607.25659/) (2026)
- [Cost-Utility Alignment in LLM Agent Trajectories:Profiling,Attribution,Diagnosis,Adaptation,and Evaluation](https://mlsanity.com/paper/2608.26195/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are increasingly developed as autonomous agents using reinforcement learning (agentic RL) that reason and act in interactive environments. However, sparse and sometimes unverifiable rewards make it extremely challenging to assign credit when training LLM agents that serve as a policy. Recent work attempts to integrate process supervision into RL but suffers from biased annotation, reward hacking, high-variance from overly fine-grained rewards or failtures when state overlap is rare. We therefore introduce implicit step rewards for agentic RL (iStar), a general credit-assignment strategy that integrates seamlessly with standard RL algorithms without relying on additional rollouts or explicit step labels. Particularly, we alternatively optimize an implicit process reward model (PRM) with the policy model to generate implicit step rewards via a trajectory-based DPO objective. Theoretical analysis shows that this learning objective produces a step-wise reward function. Then the implicit step rewards are used to compute step-level advantages, which are combined with trajectory (or episode)-level advantages for policy updates, creating a self-reinforcing training loop. We evaluate our method on three challenging agent benchmarks, including WebShop and VisualSokoban, as well as open-ended social interactions with unverifiable rewards in SOTOPIA. Crucially, iStar shows superior performance over frontier LLMs and strong RL baselines across domains, achieving state-of-the-art results with higher sample-efficiency and training stability. Further analysis also demonstrates efficient exploration by iStar with increased rewards in both step- and episode-level while maintaining fewer steps to achieve task success. Code will be available soon.