# ARIA: Training Language Agents with Intention-Driven Reward Aggregation

arXiv: https://arxiv.org/abs/2506.00539 · HTML: https://mlsanity.com/paper/2506.00539/

## Key facts

- Cited by 9 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 30 of its 49 references that are in the map.
- First posted on arXiv 31 May 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, 30 of 30)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://mlsanity.com/paper/2212.03533/) (2022)
- [ALFWorld: Aligning Text and Embodied Environments for Interactive Learning](https://mlsanity.com/paper/2010.03768/) (2020)
- [Cognitive Architectures for Language Agents](https://mlsanity.com/paper/2309.02427/) (2023)
- [SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents](https://mlsanity.com/paper/2310.11667/) (2023)
- [A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis](https://mlsanity.com/paper/2307.12856/) (2023)
- [ScienceWorld: Is your Agent Smarter than a 5th Grader?](https://mlsanity.com/paper/2203.07540/) (2022)
- [ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL](https://mlsanity.com/paper/2402.19446/) (2024)
- [Deal or No Deal? End-to-End Learning for Negotiation Dialogues](https://mlsanity.com/paper/1706.05125/) (2017)
- [Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents](https://mlsanity.com/paper/2408.07199/) (2024)
- [Large Language Model Agent: A Survey on Methodology, Applications and Challenges](https://mlsanity.com/paper/2503.21460/) (2025)
- [Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents](https://mlsanity.com/paper/2403.02502/) (2024)
- [SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks](https://mlsanity.com/paper/2503.15478/) (2025)
- [How Well Can LLMs Negotiate? NegotiationArena Platform and Analysis](https://mlsanity.com/paper/2402.05863/) (2024)
- [CLIN: A Continually Learning Language Agent for Rapid Task Adaptation and Generalization](https://mlsanity.com/paper/2310.10134/) (2023)
- [LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models](https://mlsanity.com/paper/2311.18232/) (2023)
- [Watch Every Step! LLM Agent Learning via Iterative Step-Level Process Refinement](https://mlsanity.com/paper/2406.11176/) (2024)
- [Self-playing Adversarial Language Game Enhances LLM Reasoning](https://mlsanity.com/paper/2404.10642/) (2024)
- [PRISM: Self-Pruning Intrinsic Selection Method for Training-Free Multimodal Data Selection](https://mlsanity.com/paper/2502.12119/) (2025)
- [CoT-Kinetics: A Theoretical Modeling Assessing LRM Reasoning Process](https://mlsanity.com/paper/2505.13408/) (2025)
- [Evaluating Language Model Agency through Negotiations](https://mlsanity.com/paper/2401.04536/) (2024)
- [GameEval: Evaluating LLMs on Conversational Games](https://mlsanity.com/paper/2308.10032/) (2023)
- [TimeArena: Shaping Efficient Multitasking Language Agents in a Time-Aware Simulation](https://mlsanity.com/paper/2402.05733/) (2024)
- [SelfGoal: Your Language Agents Already Know How to Achieve High-level Goals](https://mlsanity.com/paper/2406.04784/) (2024)
- [GLEE: A Unified Framework and Benchmark for Language-based Economic Environments](https://mlsanity.com/paper/2410.05254/) (2024)
- [Multi-agent KTO: Reinforcing Strategic Interactions of Large Language Model in Language Game](https://mlsanity.com/paper/2501.14225/) (2025)

## Built on by (most cited first, 9 of 9)

- [The Landscape of Agentic Reinforcement Learning for LLMs: A Survey](https://mlsanity.com/paper/2509.02547/) (2025)
- [InfoPO: Information-Driven Policy Optimization for User-Centric Agents](https://mlsanity.com/paper/2603.00656/) (2026)
- [Think Fast and Slow: Step-Level Cognitive Depth Adaptation for LLM Agents](https://mlsanity.com/paper/2602.12662/) (2026)
- [Unsupervised Learning for the Elementary Shortest Path Problem](https://mlsanity.com/paper/2508.01557/) (2025)
- [Revolutionizing Long-Term Memory in AI: New Horizons with High-Capacity and High-Speed Storage](https://mlsanity.com/paper/2602.16192/) (2026)
- [Co-Evolution of Policy and Internal Reward for Language Agents](https://mlsanity.com/paper/2604.03098/) (2026)
- [SocialRL: Refining LLMs' Social Intelligence through Multi-turn Reinforcement Learning and Reward Design](https://mlsanity.com/paper/2609.09764/) (2026)
- [Breaking the Impasse: Dual-Scale Evolutionary Policy Training for Social Language Agents](https://mlsanity.com/paper/2605.08721/) (2026)
- [Latent Action Reparameterization for Efficient Agent Inference](https://mlsanity.com/paper/2605.18597/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have enabled agents to perform complex reasoning and decision-making through free-form language interactions. However, in open-ended language action environments (e.g., negotiation or question-asking games), the action space can be formulated as a joint distribution over tokens, resulting in an exponentially large action space. Sampling actions in such a space can lead to extreme reward sparsity, which brings large reward variance, hindering effective reinforcement learning (RL). To address this, we propose ARIA, a method that Aggregates Rewards in Intention space to enable efficient and effective language Agents training. ARIA aims to project natural language actions from the high-dimensional joint token distribution space into a low-dimensional intention space, where semantically similar actions are clustered and assigned shared rewards. This intention-aware reward aggregation reduces reward variance by densifying reward signals, fostering better policy optimization. Extensive experiments demonstrate that ARIA not only significantly reduces policy gradient variance, but also delivers substantial performance gains of an average of 9.95% across four downstream tasks, consistently outperforming offline and online RL baselines.