2 citations · 4 across the 13 of their papers we have counts for
17 papers
PLE: Physical-Engineering's Last Exam
Rujun Han, Yufan Zhuang, Arijit Ray +10
Frontier language models now score above 90% on popular knowledge benchmarks and are increasingly deployed as agents that carry out multi-hour professional work. Yet no existing be…
Harness^2: Recursive Agent Harnessing for an Open World
Ruiyao Xu, Yanfei Chen, Zhongying CuiZhu +6
LLM agents' capabilities depend not only on their underlying models but also on their execution harnesses. Recursive self-improvement (RSI) offers a promising approach to automatic…
VeriHarness: Scaling Agentic Verification for Long-Horizon Tasks
Caiqi Zhang, Rujun Han, Zifeng Wang +4
As LLM agents undertake increasingly complex, long-horizon tasks, verifying their outputs becomes increasingly challenging. We study how verification capability can be strengthened…
RRSI: Regularized Recursive Self-Improvement of Agent Harnesses
Peng Xia, Rujun Han, Zifeng Wang +11
An LLM agent's capability is largely magnified by its harness, namely the prompts, control flow, tooling, memory, and context management surrounding the frozen backbone model. Rece…
EnvHarness: Awakening Static Worlds for Agent Learning
Chengsong Huang, Zifeng Wang, Rujun Han +14
LLM agents learn by interacting with environments, yet these environments are hand-built and static: blind to an agent's weaknesses, and quickly left behind as it improves. While r…
FinanceHarness: Autonomous Financial Deep Research Framework
Yijia Xiao, Rujun Han, Yanfei Chen +8
Powered by advances in LLMs and autonomous agents, deep research has become one of the most widely adopted agentic products. However, most deep research systems write general-purpo…
RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewards
Gaotang Li, Bhavana Dalvi Mishra, Zifeng Wang +9
Deep research agents plan, search, evaluate evidence, and synthesize long-form reports. Training these agents with reinforcement learning (RL) is challenging because they operate o…
SkillOS: Learning Skill Curation for Self-Evolving Agents
Siru Ouyang, Jun Yan, Yanfei Chen +13
LLM-based agents are increasingly deployed to handle streaming tasks, yet they often remain one-off problem solvers that fail to learn from past interactions. Reusable skills disti…
SAGE: Steerable Agentic Data Generation for Deep Search with Execution Feedback
Fangyuan Xu, Rujun Han, Yanfei Chen +7
Deep search agents, which aim to answer complex questions requiring reasoning across multiple documents, can significantly speed up the information-seeking process. Collecting huma…
Budget-Aware Tool Use Enables Effective Agent Scaling
Tengxiao Liu, Zifeng Wang, Jin Miao +12
Scaling test-time computation has been extended from language model reasoning to tool-augmented agents, where scaling involves not only thinking in tokens but also acting via tool…
COMPASS: Enhancing Agent Long-Horizon Reasoning with Evolving Context
Guangya Wan, Mingyang Ling, Xiaoqi Ren +3
Long-horizon tasks that require sustained reasoning and multiple tool interactions remain challenging for LLM agents: small errors compound across steps, and even state-of-the-art…
Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning
Yihe Deng, I-Hung Hsu, Jun Yan +7
Large Language Models (LLMs) often struggle with problems that require multi-step reasoning. For small-scale open-source models, Reinforcement Learning with Verifiable Rewards (RLV…
ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory
Siru Ouyang, Jun Yan, I-Hung Hsu +14
With the growing adoption of large language model agents in persistent real-world roles, they naturally encounter continuous streams of tasks. A key limitation, however, is their f…
Towards Compute-Optimal Many-Shot In-Context Learning
Shahriar Golchin, Yanfei Chen, Rujun Han +7
Long-context large language models (LLMs) are able to process inputs containing up to several million tokens. In the scope of in-context learning (ICL), this translates into using…
In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents
Zhen Tan, Jun Yan, I-Hung Hsu +12
Large Language Models (LLMs) have made significant progress in open-ended dialogue, yet their inability to retain and retrieve relevant information from long-term interactions limi…
Reverse Thinking Makes LLMs Stronger Reasoners
Justin Chih-Yao Chen, Zifeng Wang, Hamid Palangi +8
Reverse thinking plays a crucial role in human reasoning. Humans can reason not only from a problem to a solution but also in reverse, i.e., start from the solution and reason towa…
Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved Sampling
Wenda Xu, Rujun Han, Zifeng Wang +7
Recent advances in knowledge distillation (KD) have enabled smaller student models to approach the performance of larger teacher models. However, popular methods such as supervised…