Boosting Virtual Agent Learning and Reasoning: A Step-wise, Multi-dimensional, and Generalist Reward Model with Benchmark

• URL: http://arxiv.org/abs/2503.18665v1
• Date: Mon, 24 Mar 2025 13:30:47 GMT
• Title: Boosting Virtual Agent Learning and Reasoning: A Step-wise, Multi-dimensional, and Generalist Reward Model with Benchmark
• Authors: Bingchen Miao, Yang Wu, Minghe Gao, Qifan Yu, Wendong Bu, Wenqiao Zhang, Yunfei Li, Siliang Tang, Tat-Seng Chua, Juncheng Li,
• Abstract summary: We propose Similar, a step-wise Multi-dimensional Generalist Reward Model.<n>It offers fine-grained signals for agent training and can choose better action for inference-time scaling.<n>We introduce the first benchmark in the virtual agent domain for step-wise, multi-dimensional reward model training and evaluation.
• Score: 72.46357004059661
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The development of Generalist Virtual Agents (GVAs) powered by Multimodal Large Language Models (MLLMs) has shown significant promise in autonomous task execution. However, current training paradigms face critical limitations, including reliance on outcome supervision and labor-intensive human annotations. To address these challenges, we propose Similar, a Step-wise Multi-dimensional Generalist Reward Model, which offers fine-grained signals for agent training and can choose better action for inference-time scaling. Specifically, we begin by systematically defining five dimensions for evaluating agent actions. Building on this framework, we design an MCTS-P algorithm to automatically collect and annotate step-wise, five-dimensional agent execution data. Using this data, we train Similar with the Triple-M strategy. Furthermore, we introduce the first benchmark in the virtual agent domain for step-wise, multi-dimensional reward model training and evaluation, named SRM. This benchmark consists of two components: SRMTrain, which serves as the training set for Similar, and SRMEval, a manually selected test set for evaluating the reward model. Experimental results demonstrate that Similar, through its step-wise, multi-dimensional assessment and synergistic gain, provides GVAs with effective intermediate signals during both training and inference-time scaling. The code is available at https://github.com/Galery23/Similar-v1.

Related papers

• APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay [86.01901238059261]
  APIGen-MT is a framework that generates verifiable and diverse multi-turn agent data. We train a family of models -- the xLAM-2-fc-r series with sizes ranging from 1B to 70B parameters. Our models outperform frontier models such as GPT-4o and Claude 3.5 on $tau$-bench and BFCL benchmarks.
  arXiv  Detail & Related papers  (2025-04-04T17:13:57Z)
• GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning [35.429904556288996]
  We introduce GenPRM, a generative process reward model that performs explicit Chain-of-Thought (CoT) reasoning with code verification. Experimental results show that GenPRM significantly outperforms prior PRMs with only 23K training data from MATH dataset.
  arXiv  Detail & Related papers  (2025-04-01T15:21:05Z)
• DARS: Dynamic Action Re-Sampling to Enhance Coding Agent Performance by Adaptive Tree Traversal [55.13854171147104]
  Large Language Models (LLMs) have revolutionized various domains, including natural language processing, data analysis, and software development. We present Dynamic Action Re-Sampling (DARS), a novel inference time compute scaling approach for coding agents. We evaluate our approach on SWE-Bench Lite benchmark, demonstrating that this scaling strategy achieves a pass@k score of 55% with Claude 3.5 Sonnet V2.
  arXiv  Detail & Related papers  (2025-03-18T14:02:59Z)
• VisualPRM: An Effective Process Reward Model for Multimodal Reasoning [76.35753243272521]
  We introduce VisualPRM, which improves the reasoning abilities of existing Multimodal Large Language Models (MLLMs)<n>Our model achieves a 5.9-point improvement across seven multimodal reasoning benchmarks.<n>For the evaluation of multimodal PRMs, we propose VisualProcessBench, a benchmark with human-annotated step-wise correctness labels.
  arXiv  Detail & Related papers  (2025-03-13T12:03:37Z)
• Process Reward Models for LLM Agents: Practical Framework and Directions [10.986389591866617]
  We introduce Agent Process Reward Models (AgentPRM), a framework for training LLM agents to continually improve through interactions.<n>We propose InversePRM, which learns process rewards directly from demonstrations without explicit outcome supervision.<n>We evaluate on ALFWorld benchmark, show that small 3B models trained with AgentPRM and InversePRM outperform strong GPT-4o baselines.
  arXiv  Detail & Related papers  (2025-02-14T17:34:28Z)
• Sports-Traj: A Unified Trajectory Generation Model for Multi-Agent Movement in Sports [53.637837706712794]
  We propose a Unified Trajectory Generation model, UniTraj, that processes arbitrary trajectories as masked inputs.<n>Specifically, we introduce a Ghost Spatial Masking (GSM) module, embedded within a Transformer encoder, for spatial feature extraction.<n>We benchmark three practical sports datasets, Basketball-U, Football-U, and Soccer-U, for evaluation.
  arXiv  Detail & Related papers  (2024-05-27T22:15:23Z)
• The Fine Line: Navigating Large Language Model Pretraining with Down-streaming Capability Analysis [27.310894780313618]
  This paper undertakes a comprehensive comparison of model capabilities at various pretraining intermediate checkpoints. We confirm that specific downstream metrics exhibit similar training dynamics across models of different sizes. In addition to our core findings, we've reproduced Amber and OpenLLaMA, releasing their intermediate checkpoints.
  arXiv  Detail & Related papers  (2024-04-01T16:00:01Z)
• Meta-training with Demonstration Retrieval for Efficient Few-shot Learning [11.723856248352007]
  Large language models show impressive results on few-shot NLP tasks. These models are memory and computation-intensive. We propose meta-training with demonstration retrieval.
  arXiv  Detail & Related papers  (2023-06-30T20:16:22Z)
• Evaluating Representations with Readout Model Switching [19.907607374144167]
  In this paper, we propose to use the Minimum Description Length (MDL) principle to devise an evaluation metric. We design a hybrid discrete and continuous-valued model space for the readout models and employ a switching strategy to combine their predictions. The proposed metric can be efficiently computed with an online method and we present results for pre-trained vision encoders of various architectures.
  arXiv  Detail & Related papers  (2023-02-19T14:08:01Z)
• ZhichunRoad at Amazon KDD Cup 2022: MultiTask Pre-Training for E-Commerce Product Search [4.220439000486713]
  We propose a robust multilingual model to improve the quality of search results. In pre-training stage, we adopt mlm task, classification task and contrastive learning task. In fine-tuning stage, we use confident learning, exponential moving average method (EMA), adversarial training (FGM) and regularized dropout strategy (R-Drop)
  arXiv  Detail & Related papers  (2023-01-31T07:31:34Z)
• SUPERB-SG: Enhanced Speech processing Universal PERformance Benchmark for Semantic and Generative Capabilities [76.97949110580703]
  We introduce SUPERB-SG, a new benchmark to evaluate pre-trained models across various speech tasks. We use a lightweight methodology to test the robustness of representations learned by pre-trained models under shifts in data domain. We also show that the task diversity of SUPERB-SG coupled with limited task supervision is an effective recipe for evaluating the generalizability of model representation.
  arXiv  Detail & Related papers  (2022-03-14T04:26:40Z)
• Multitask Adaptation by Retrospective Exploration with Learned World Models [77.34726150561087]
  We propose a meta-learned addressing model called RAMa that provides training samples for the MBRL agent taken from task-agnostic storage. The model is trained to maximize the expected agent's performance by selecting promising trajectories solving prior tasks from the storage.
  arXiv  Detail & Related papers  (2021-10-25T20:02:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.