Cover Image

Agent-RLVR: Training Software Engineering Agents via Guidance and Environment Rewards

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Da, Jeff, Wang, Clinton, Deng, Xiang, Ma, Yuntao, Barhate, Nikhil, Hendryx, Sean
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Adaptive Guidance Accelerates Reinforcement Learning of Reasoning Models
by: Nath, Vaskar, et al.
Published: (2025)

Learning Goal-Conditioned Representations for Language Reward Models
by: Nath, Vaskar, et al.
Published: (2024)

Terminal-World: Scaling Terminal-Agent Environments via Agent Skills
by: Cheng, Zihao, et al.
Published: (2026)

Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains
by: Gunjal, Anisha, et al.
Published: (2025)

Agents in Software Engineering: Survey, Landscape, and Vision
by: Wang, Yanlin, et al.
Published: (2024)

Process-Level Trajectory Evaluation for Environment Configuration in Software Engineering Agents
by: Kuang, Jiayi, et al.
Published: (2025)

Revisiting the Superficial Alignment Hypothesis
by: Raghavendra, Mohit, et al.
Published: (2024)

Recycling Failures: Salvaging Exploration in RLVR via Fine-Grained Off-Policy Guidance
by: Ren, Yanwei, et al.
Published: (2026)

Effective Strategies for Asynchronous Software Engineering Agents
by: Geng, Jiayi, et al.
Published: (2026)

Detecting RLVR Training Data via Structural Convergence of Reasoning
by: Zhang, Hongbo, et al.
Published: (2026)

Improving Grounded Language Understanding in a Collaborative Environment by Interacting with Agents Through Help Feedback
by: Mehta, Nikhil, et al.
Published: (2023)

Agentless: Demystifying LLM-based Software Engineering Agents
by: Xia, Chunqiu Steven, et al.
Published: (2024)

PerMix-RLVR: Preserving Persona Expressivity under Verifiable-Reward Alignment
by: Oh, Jihwan, et al.
Published: (2026)

EnigmaEval: A Benchmark of Long Multimodal Reasoning Challenges
by: Wang, Clinton J., et al.
Published: (2025)

MedExAgent: Training LLM Agents to Ask, Examine, and Diagnose in Noisy Clinical Environments
by: Gao, Yicheng, et al.
Published: (2026)

ResearchRubrics: A Benchmark of Prompts and Rubrics For Evaluating Deep Research Agents
by: Sharma, Manasi, et al.
Published: (2025)

Scalable Environments Drive Generalizable Agents
by: Zhang, Jiayi, et al.
Published: (2026)

Countdown-Code: A Testbed for Studying The Emergence and Generalization of Reward Hacking in RLVR
by: Khalifa, Muhammad, et al.
Published: (2026)

SWE-smith: Scaling Data for Software Engineering Agents
by: Yang, John, et al.
Published: (2025)

Adaptive Milestone Reward for GUI Agents
by: Zheng, Congmin, et al.
Published: (2026)

Exploring Reasoning Reward Model for Agents
by: Fan, Kaixuan, et al.
Published: (2026)

Training Versatile Coding Agents in Synthetic Environments
by: Zhu, Yiqi, et al.
Published: (2025)

AgentCE-Bench: Agent Configurable Evaluation with Scalable Horizons and Controllable Difficulty under Lightweight Environments
by: Yang, Wang, et al.
Published: (2026)

OmniCode: A Benchmark for Evaluating Software Engineering Agents
by: Sonwane, Atharv, et al.
Published: (2026)

Training Proactive and Personalized LLM Agents
by: Sun, Weiwei, et al.
Published: (2025)

Training a Generally Curious Agent
by: Tajwar, Fahim, et al.
Published: (2025)

EnvGen: Generating and Adapting Environments via LLMs for Training Embodied Agents
by: Zala, Abhay, et al.
Published: (2024)

CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewards
by: Xue, Xiangyuan, et al.
Published: (2025)

Exploration vs Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward
by: Chen, Peter, et al.
Published: (2025)

RLVER: Reinforcement Learning with Verifiable Emotion Rewards for Empathetic Agents
by: Wang, Peisong, et al.
Published: (2025)

SyncMind: Measuring Agent Out-of-Sync Recovery in Collaborative Software Engineering
by: Guo, Xuehang, et al.
Published: (2025)

Agent-RewardBench: Towards a Unified Benchmark for Reward Modeling across Perception, Planning, and Safety in Real-World Multimodal Agents
by: Men, Tianyi, et al.
Published: (2025)

AgentRM: Enhancing Agent Generalization with Reward Modeling
by: Xia, Yu, et al.
Published: (2025)

Agent Lumos: Unified and Modular Training for Open-Source Language Agents
by: Yin, Da, et al.
Published: (2023)

LLM-Based Offline Learning for Embodied Agents via Consistency-Guided Reward Ensemble
by: Lee, Yujeong, et al.
Published: (2024)

Reasoning Depth and Environment Complexity: A Controlled Study of RLVR Data Allocation across Logical Reasoning Tasks
by: Zhu, Yihua, et al.
Published: (2026)

Cognitive Kernel-Pro: A Framework for Deep Research Agents and Agent Foundation Models Training
by: Fang, Tianqing, et al.
Published: (2025)

ARE: Scaling Up Agent Environments and Evaluations
by: Froger, Romain, et al.
Published: (2025)

IntelliAsk: Learning to Ask High-Quality Research Questions via RLVR
by: Sharma, Karun, et al.
Published: (2026)

CRAFT: Grounded Multi-Agent Coordination Under Partial Information
by: Nath, Abhijnan, et al.
Published: (2026)