7 papers · 1 filter
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…
Rethinking Scientific Discovery in the Agentic Era
Yining Zheng, Yuxin Wang, Jiahao Lu +27
Artificial intelligence has advanced scientific discovery, but most AI4Science systems remain fragmented tools that rely on humans to coordinate problem formulation, literature gro…
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-…
AgentLongBench: A Controllable Long Benchmark For Long-Contexts Agents via Environment Rollouts
Shicheng Fang, Yuxin Wang, Xiaoran Liu +6
The evolution of Large Language Models (LLMs) into autonomous agents necessitates the management of extensive, dynamic contexts. Current benchmarks, however, remain largely static,…
Multi-hop Reasoning via Early Knowledge Alignment
Yuxin Wang, Shicheng Fang, Bo Wang +4
Retrieval-Augmented Generation (RAG) has emerged as a powerful paradigm for Large Language Models (LLMs) to address knowledge-intensive queries requiring domain-specific or up-to-d…
MARAG-R1: Beyond Single Retriever via Reinforcement-Learned Multi-Tool Agentic Retrieval
Qi Luo, Xiaonan Li, Yuxin Wang +4
Large Language Models (LLMs) excel at reasoning and generation but are inherently limited by static pretraining data, resulting in factual inaccuracies and weak adaptability to new…