8 papers
Learn from Move: the Next Step for GUI Agents
Jiahao Lu, Yize Shen, Chuanyuan Tan +6
Existing benchmarks for GUI agents primarily focus on increasing task difficulty by extending task horizons. Besides, enabling agents to explore unfamiliar environments and success…
MARCO: Multi-Round Agentic Reinforcement for Conditional Molecular Optimization
Shicheng Fang, Yuxin Wang, Zhuo Yang +6
Molecular optimization is inherently iterative: a candidate is proposed, evaluated against several objectives, and revised while preserving a relationship to the source molecule. M…
ORPG: Reconciling Multiple Reward Objectives through Objective-wise Policy Gradients
Shicheng Fang, Yiwen Zhao, Wenbo Tian +4
Multi-reward policy optimization requires a joint update that reflects both the learning signals and the intended relationships among objectives. We introduce Objective-wise Reconc…
SWE-bench Science: Can Coding Agents Resolve Engineering Tasks in Science?
Zhipeng Xu, Jiahao Lu, Yining Zheng +2
Software increasingly functions as part of the scientific instrument itself, making failures in scientific code capable of compromising not only program behavior but also the evide…
What Makes Agent Memory Useful for Reliable Unanswerable Question Handling?
Chuanyuan Tan, Junjie Yu, Yuxin Wang +3
Reliable handling of unanswerable questions (UAQs) is critical for trustworthy LLM-based agents. Although memory is widely used in agent systems, its role in reliable UAQ handling…
AdaptR1: Reinforcement Learning Based Adaptive Interleaved Thinking in Multi-hop Question Answering
Yuxin Wang, Jiahao Lu, Qifeng Wu +5
Large Language Models (LLMs) have achieved remarkable performance in complex reasoning tasks through Chain-of-Thought (CoT) prompting. However, this approach often leads to ``over-…
Beyond Rating: A Comprehensive Evaluation and Benchmark for AI Reviews
Bowen Li, Haochen Ma, Yuxin Wang +5
The rapid adoption of Large Language Models (LLMs) has spurred interest in automated peer review; however, progress is currently stifled by benchmarks that treat reviewing primaril…
Balanced Aggregation: Understanding and Fixing Aggregation Bias in GRPO
Zhiyuan Zeng, Jiameng Huang, Zhangyue Yin +8
Reinforcement learning with verifiable rewards (RLVR) has become a central paradigm for improving reasoning and code generation in large language models, and GRPO-style training is…