11 papers
Distillation as Probability Transport: Routed On-Policy Distillation
Tianle Xia, Lingxiang Hu, Yiding Sun +6
On-policy distillation (OPD) transfers teacher knowledge on student-generated trajectories, but efficient sampled objectives reduce the teacher distribution to scalar credit on ind…
Teaching a Moving Student: Rethinking the Curriculum of On-Policy Distillation
Lingxiang Hu, Tianle Xia, Ming Xu +6
In on-policy distillation (OPD), the student determines which states receive teacher supervision. As its policy evolves, earlier response prefixes become less likely even though te…
When Self-Evolution Backfires: Pre-Commit Gating against Skill Contamination in LLM Agents
Linfang Shang, Ming Xu, Yiding Sun +4
Self-evolving agents accumulate capability by distilling reusable skills from their execution trajectories, but we find this process is not monotonic: past a critical pool size, ne…
GraSP: Graph-Structured Skill Compositions for LLM Agents
Tianle Xia, Lingxiang Hu, Yiding Sun +5
Skill ecosystems for LLM agents have matured rapidly, yet recent benchmarks show that providing agents with more skills does not monotonically improve performance -- focused sets o…
Towards Faithful Industrial RAG: A Reinforced Co-adaptation Framework for Advertising QA
Wenwei Li, Ming Xu, Tianle Xia +7
Industrial advertising question answering (QA) is a high-stakes task in which hallucinated content, particularly fabricated URLs, can lead to financial loss, compliance violations,…
Search-P1: Path-Centric Reward Shaping for Stable and Efficient Agentic RAG Training
Tianle Xia, Ming Xu, Lingxiang Hu +7
Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by incorporating external knowledge, yet traditional single-round retrieval struggles with complex multi-…
AD-Bench: A Real-World, Trajectory-Aware Advertising Analytics Benchmark for LLM Agents
Lingxiang Hu, Yiding Sun, Tianle Xia +6
While Large Language Model (LLM) agents have made remarkable progress on complex reasoning, evaluating them in real-world environments remains an open problem. Existing benchmarks…
Compass-Embedding v4: Robust Contrastive Learning for Multilingual E-commerce Embeddings
Pakorn Ueareeworakul, Shuman Liu, Jinghao Feng +7
As global e-commerce rapidly expands into emerging markets, the lack of high-quality semantic representations for low-resource languages has become a decisive bottleneck for retrie…
Each Prompt Matters: Scaling Reinforcement Learning Without Wasting Rollouts on Hundred-Billion-Scale MoE
Anxiang Zeng, Haibo Zhang, Hailing Zhang +13
We present CompassMax-V3-Thinking, a hundred-billion-scale MoE reasoning model trained with a new RL framework built on one principle: each prompt must matter. Scaling RL to this s…
Towards Reliable Evaluation of Large Language Models for Multilingual and Multimodal E-Commerce Applications
Shuyi Xie, Ziqin Liew, Hailing Zhang +5
Large Language Models (LLMs) excel on general-purpose NLP benchmarks, yet their capabilities in specialized domains remain underexplored. In e-commerce, existing evaluations-such a…
MEETING DELEGATE: Benchmarking LLMs on Attending Meetings on Our Behalf
Lingxiang Hu, Shurun Yuan, Xiaoting Qin +5
In contemporary workplaces, meetings are essential for exchanging ideas and ensuring team alignment but often face challenges such as time consumption, scheduling conflicts, and in…