Image de couverture de livre

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

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Da, Jeff, Wang, Clinton, Deng, Xiang, Ma, Yuntao, Barhate, Nikhil, Hendryx, Sean
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Adaptive Guidance Accelerates Reinforcement Learning of Reasoning Models
par: Nath, Vaskar, et autres
Publié: (2025)

Learning Goal-Conditioned Representations for Language Reward Models
par: Nath, Vaskar, et autres
Publié: (2024)

Terminal-World: Scaling Terminal-Agent Environments via Agent Skills
par: Cheng, Zihao, et autres
Publié: (2026)

Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains
par: Gunjal, Anisha, et autres
Publié: (2025)

Agents in Software Engineering: Survey, Landscape, and Vision
par: Wang, Yanlin, et autres
Publié: (2024)

Process-Level Trajectory Evaluation for Environment Configuration in Software Engineering Agents
par: Kuang, Jiayi, et autres
Publié: (2025)

Revisiting the Superficial Alignment Hypothesis
par: Raghavendra, Mohit, et autres
Publié: (2024)

Recycling Failures: Salvaging Exploration in RLVR via Fine-Grained Off-Policy Guidance
par: Ren, Yanwei, et autres
Publié: (2026)

Effective Strategies for Asynchronous Software Engineering Agents
par: Geng, Jiayi, et autres
Publié: (2026)

Detecting RLVR Training Data via Structural Convergence of Reasoning
par: Zhang, Hongbo, et autres
Publié: (2026)

Improving Grounded Language Understanding in a Collaborative Environment by Interacting with Agents Through Help Feedback
par: Mehta, Nikhil, et autres
Publié: (2023)

Agentless: Demystifying LLM-based Software Engineering Agents
par: Xia, Chunqiu Steven, et autres
Publié: (2024)

PerMix-RLVR: Preserving Persona Expressivity under Verifiable-Reward Alignment
par: Oh, Jihwan, et autres
Publié: (2026)

EnigmaEval: A Benchmark of Long Multimodal Reasoning Challenges
par: Wang, Clinton J., et autres
Publié: (2025)

MedExAgent: Training LLM Agents to Ask, Examine, and Diagnose in Noisy Clinical Environments
par: Gao, Yicheng, et autres
Publié: (2026)

ResearchRubrics: A Benchmark of Prompts and Rubrics For Evaluating Deep Research Agents
par: Sharma, Manasi, et autres
Publié: (2025)

Scalable Environments Drive Generalizable Agents
par: Zhang, Jiayi, et autres
Publié: (2026)

Countdown-Code: A Testbed for Studying The Emergence and Generalization of Reward Hacking in RLVR
par: Khalifa, Muhammad, et autres
Publié: (2026)

SWE-smith: Scaling Data for Software Engineering Agents
par: Yang, John, et autres
Publié: (2025)

Adaptive Milestone Reward for GUI Agents
par: Zheng, Congmin, et autres
Publié: (2026)

Exploring Reasoning Reward Model for Agents
par: Fan, Kaixuan, et autres
Publié: (2026)

Training Versatile Coding Agents in Synthetic Environments
par: Zhu, Yiqi, et autres
Publié: (2025)

AgentCE-Bench: Agent Configurable Evaluation with Scalable Horizons and Controllable Difficulty under Lightweight Environments
par: Yang, Wang, et autres
Publié: (2026)

OmniCode: A Benchmark for Evaluating Software Engineering Agents
par: Sonwane, Atharv, et autres
Publié: (2026)

Training Proactive and Personalized LLM Agents
par: Sun, Weiwei, et autres
Publié: (2025)

Training a Generally Curious Agent
par: Tajwar, Fahim, et autres
Publié: (2025)

EnvGen: Generating and Adapting Environments via LLMs for Training Embodied Agents
par: Zala, Abhay, et autres
Publié: (2024)

CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewards
par: Xue, Xiangyuan, et autres
Publié: (2025)

Exploration vs Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward
par: Chen, Peter, et autres
Publié: (2025)

RLVER: Reinforcement Learning with Verifiable Emotion Rewards for Empathetic Agents
par: Wang, Peisong, et autres
Publié: (2025)

SyncMind: Measuring Agent Out-of-Sync Recovery in Collaborative Software Engineering
par: Guo, Xuehang, et autres
Publié: (2025)

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

AgentRM: Enhancing Agent Generalization with Reward Modeling
par: Xia, Yu, et autres
Publié: (2025)

Agent Lumos: Unified and Modular Training for Open-Source Language Agents
par: Yin, Da, et autres
Publié: (2023)

LLM-Based Offline Learning for Embodied Agents via Consistency-Guided Reward Ensemble
par: Lee, Yujeong, et autres
Publié: (2024)

Reasoning Depth and Environment Complexity: A Controlled Study of RLVR Data Allocation across Logical Reasoning Tasks
par: Zhu, Yihua, et autres
Publié: (2026)

Cognitive Kernel-Pro: A Framework for Deep Research Agents and Agent Foundation Models Training
par: Fang, Tianqing, et autres
Publié: (2025)

ARE: Scaling Up Agent Environments and Evaluations
par: Froger, Romain, et autres
Publié: (2025)

IntelliAsk: Learning to Ask High-Quality Research Questions via RLVR
par: Sharma, Karun, et autres
Publié: (2026)

CRAFT: Grounded Multi-Agent Coordination Under Partial Information
par: Nath, Abhijnan, et autres
Publié: (2026)