# AgentRM: Enhancing Agent Generalization with Reward Modeling

arXiv: https://arxiv.org/abs/2502.18407 · HTML: https://mlsanity.com/paper/2502.18407/

## Key facts

- Cited by 27 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 37 of its 57 references that are in the map.
- First posted on arXiv 25 Feb 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 37)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [Mind2Web: Towards a Generalist Agent for the Web](https://mlsanity.com/paper/2306.06070/) (2023)
- [Solving math word problems with process- and outcome-based feedback](https://mlsanity.com/paper/2211.14275/) (2022)
- [Large Language Models Can Self-Improve](https://mlsanity.com/paper/2210.11610/) (2022)
- [Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models](https://mlsanity.com/paper/2401.01335/) (2024)
- [Augmented Language Models: a Survey](https://mlsanity.com/paper/2302.07842/) (2023)
- [ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search](https://mlsanity.com/paper/2406.03816/) (2024)
- [AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents](https://mlsanity.com/paper/2401.13178/) (2024)
- [AgentTuning: Enabling Generalized Agent Abilities for LLMs](https://mlsanity.com/paper/2310.12823/) (2023)
- [FireAct: Toward Language Agent Fine-tuning](https://mlsanity.com/paper/2310.05915/) (2023)
- [Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents](https://mlsanity.com/paper/2408.07199/) (2024)
- [Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents](https://mlsanity.com/paper/2403.02502/) (2024)
- [Free Process Rewards without Process Labels](https://mlsanity.com/paper/2412.01981/) (2024)
- [AgentGym: Evolving Large Language Model-based Agents across Diverse Environments](https://mlsanity.com/paper/2406.04151/) (2024)
- [Q*: Improving Multi-step Reasoning for LLMs with Deliberative Planning](https://mlsanity.com/paper/2406.14283/) (2024)
- [Watch Every Step! LLM Agent Learning via Iterative Step-Level Process Refinement](https://mlsanity.com/paper/2406.11176/) (2024)
- [AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generation](https://mlsanity.com/paper/2408.00764/) (2024)
- [Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training](https://mlsanity.com/paper/2501.11425/) (2025)
- [Agent Lumos: Unified and Modular Training for Open-Source Language Agents](https://mlsanity.com/paper/2311.05657/) (2023)

## Built on by (most cited first, 27 of 27)

- [AgentPRM: Process Reward Models for LLM Agents via Step-Wise Promise and Progress](https://mlsanity.com/paper/2511.08325/) (2025)
- [UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents](https://mlsanity.com/paper/2505.21496/) (2025)
- [DeepWideSearch: Benchmarking Depth and Width in Agentic Information Seeking](https://mlsanity.com/paper/2510.20168/) (2025)
- [AssetOpsBench: Benchmarking AI Agents for Task Automation in Industrial Asset Operations and Maintenance](https://mlsanity.com/paper/2506.03828/) (2025)
- [Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards](https://mlsanity.com/paper/2505.02686/) (2025)
- [SAND: Boosting LLM Agents with Self-Taught Action Deliberation](https://mlsanity.com/paper/2507.07441/) (2025)
- [Agentic Artificial Intelligence (AI): Architectures, Taxonomies, and Evaluation of Large Language Model Agents](https://mlsanity.com/paper/2601.12560/) (2026)
- [Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning](https://mlsanity.com/paper/2509.22601/) (2025)
- [Enhancing Large Language Model Reasoning with Reward Models: An Analytical Survey](https://mlsanity.com/paper/2510.01925/) (2025)
- [Guideline-Grounded Evidence Accumulation for High-Stakes Agent Verification](https://mlsanity.com/paper/2603.02798/) (2026)
- [CoSineVerifier: Tool-Augmented Answer Verification for Computation-Oriented Scientific Questions](https://mlsanity.com/paper/2512.01224/) (2025)
- [Enhancing LLMs' Reasoning-Intensive Multimedia Search Capabilities through Fine-Tuning and Reinforcement Learning](https://mlsanity.com/paper/2505.18831/) (2025)
- [3D CoCa v2: Contrastive Learners with Test-Time Search for Generalizable Spatial Intelligence](https://mlsanity.com/paper/2601.06496/) (2026)
- [Supervised Fine-Tuning versus Reinforcement Learning: A Study of Post-Training Methods for Large Language Models](https://mlsanity.com/paper/2603.13985/) (2026)
- [Don't Solve, Just Compare: Tiny Advisors for Runtime Intervention in LLM Agents](https://mlsanity.com/paper/2608.21027/) (2026)
- [AutoContext: Instance-Level Context Learning for LLM Agents](https://mlsanity.com/paper/2510.02369/) (2025)
- [IntentScore: Intent-Conditioned Action Evaluation for Computer-Use Agents](https://mlsanity.com/paper/2604.05157/) (2026)
- [Every Step Counts: Step-Level Credit Assignment for Tool-Integrated Text-to-SQL](https://mlsanity.com/paper/2605.04719/) (2026)
- [Tree-based Credit Assignment for Multi-Agent Memory System](https://mlsanity.com/paper/2605.04811/) (2026)
- [Semantic Consistency Policy Optimization for Reinforcement Learning of LLM Agents](https://mlsanity.com/paper/2606.25852/) (2026)
- [Task-Adaptive Rubrics for GUI Reward Modeling](https://mlsanity.com/paper/2608.24174/) (2026)
- [AgentXRay: White-Boxing Agentic Systems via Workflow Reconstruction](https://mlsanity.com/paper/2602.05353/) (2026)
- [Humans' ALMANAC: A Human Collaboration Dataset of Action-Level Mental Model Annotations for Agent Collaboration](https://mlsanity.com/paper/2606.06388/) (2026)
- [AutoVerifier: Residual-Guided Non-Parametric Optimization for Reference-Based Answer Verification](https://mlsanity.com/paper/2608.25637/) (2026)
- [JET: Judge-Guided Evolution at Test Time for Agent Programs](https://mlsanity.com/paper/2609.34126/) (2026)
- [Of Errors and Echoes: Responsibility-Aware Credit Assignment for Tool-Use Agents](https://mlsanity.com/paper/2610.16027/) (2026)
- [Reading Right, Acting Wrong: Diagnosing Decision Failures of System One Models in Agent Loops](https://mlsanity.com/paper/2610.18579/) (2026)

## Abstract (arXiv)

Existing LLM-based agents have achieved strong performance on held-in tasks, but their generalizability to unseen tasks remains poor. Hence, some recent work focus on fine-tuning the policy model with more diverse tasks to improve the generalizability. In this work, we find that finetuning a reward model to guide the policy model is more robust than directly finetuning the policy model. Based on this finding, we propose AgentRM, a generalizable reward model, to guide the policy model for effective test-time search. We comprehensively investigate three approaches to construct the reward model, including explicit reward modeling, implicit reward modeling and LLM-as-a-judge. We then use AgentRM to guide the answer generation with Best-of-N sampling and step-level beam search. On four types of nine agent tasks, AgentRM enhances the base policy model by 8.8 points on average, surpassing the top general agent by 4.0. Moreover, it demonstrates weak-to-strong generalization, yielding greater improvement of 12.6 on LLaMA-3-70B policy model. As for the specializability, AgentRM can also boost a finetuned policy model and outperform the top specialized agent by 11.4 on three held-in tasks. Further analysis verifies its effectiveness in test-time scaling. Codes will be released to facilitate the research in this area.