5 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…
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…
Mitigating False Credit Propagation: Probabilistic Graphical Reward Aggregation for Rubric-Based Reinforcement Learning
Can Lv, Mingju Chen, Heng Chang +1
Rubric-based rewards are increasingly used for open-ended language model post-training, but criterion-level scores are often aggregated as independent utilities. This flat scalariz…
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…
All-Mem: Agentic Lifelong Memory via Dynamic Topology Evolution
Can Lv, Heng Chang, Shengyu Tao +5
Lifelong interactive agents are expected to assist users over months or years, which requires continually writing long term memories while retrieving the right evidence for each ne…