7 papers
Beyond Timestamps: Decision-Aligned On-Policy Distillation for Long-Horizon Agents
Mingju Chen, Can Lv, Jinrong Liu +3
Reinforcement learning with verifiable rewards (RLVR) often relies on sparse outcome rewards, providing coarse supervision for long-horizon agents. On-policy self-distillation (OPS…
JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolution
Guibin Zhang, Leo Lu, Fangzhou Xie +15
Agent capability is not determined by the model alone. The agent harness, encompassing memory management, planning strategy, action protocol, and tool/skill orchestration, can domi…
TRCA: Transition-wise Rubric Credit Assignment for Long-horizon LLM Agents
Huan Zhang, Mingju Chen, Dongxu Zhou +5
Long-horizon large language model (LLM) agents are typically optimized with sparse terminal outcomes, making fine-grained credit assignment across multi-step interactions difficult…
HarnessForge: Joint Harness and Policy Evolution for Adaptive Agent Systems
Mingju Chen, Can Lv, Guibin Zhang +2
LLM agents are increasingly expected to operate across heterogeneous task regimes that require distinct execution paradigms. This challenges fixed agent systems and motivates syste…
TodoEvolve: Learning to Architect Agent Planning Systems
Jiaxi Liu, Yanzuo Jiang, Guibin Zhang +5
Planning has become a central capability for contemporary agent systems in navigating complex, long-horizon tasks, yet existing approaches predominantly rely on fixed, hand-crafted…
A-MapReduce: Executing Wide Search via Agentic MapReduce
Mingju Chen, Guibin Zhang, Heng Chang +3
Contemporary large language model (LLM)-based multi-agent systems exhibit systematic advantages in deep research tasks, which emphasize iterative, vertically structured information…
EvoFlow: Evolving Diverse Agentic Workflows On The Fly
Guibin Zhang, Kaijie Chen, Guancheng Wan +5
The past two years have witnessed the evolution of large language model (LLM)-based multi-agent systems from labor-intensive manual design to partial automation (\textit{e.g.}, pro…