11 papers
AREX: Towards a Recursively Self-Improving Agent for Deep Research
Shuqi Lu, Chaofan Li, Kun Luo +21
Deep research requires agents to find answers that jointly satisfy multiple constraints. Discovering such answers is costly, whereas verifying a candidate can often be decomposed i…
OPOD: On-Policy Omni Distillation
Tong Zhao, Yuyang Hu, Reed Li +5
Omni-modal models provide a unified interface for text, images, and audio. However, improving these abilities together remains difficult, as post-training on pooled multimodal data…
MemSifter: Offloading LLM Memory Retrieval via Outcome-Driven Proxy Reasoning
Jiejun Tan, Zhicheng Dou, Liancheng Zhang +3
As Large Language Models (LLMs) are increasingly used for long-duration tasks, maintaining effective long-term memory has become a critical challenge. Current methods often face a…
VeriGraph: Towards Verifiable Data-Analytic Agents
Jiajie Jin, Zhao Yang, Wenle Liao +5
LLM-based agents have demonstrated strong capabilities in data-intensive analytical tasks, yet their outputs are rarely verifiable: a reliance on linear text trajectories makes the…
Toward Generalist Autonomous Research via Hypothesis-Tree Refinement
Jiajie Jin, Yuyang Hu, Kai Qiu +15
Scientific progress depends on a repeated loop of exploration, experimentation, and abstraction. Researchers test candidate directions, interpret the evidence, and carry the result…
From Player to Master: Enhancing Test-Time Learning of LLM Agents via Reinforcement Learning over Memory
Yishuo Cai, Xingyu Guo, Xuancheng Huang +8
Large language model (LLM) agents are increasingly deployed in long-running settings where improving through experience at test time becomes important. A common approach is to upda…