collaborators

15 papers

cs.AI2026

Matching Supervision to the Student's Learning Capacity: A Unified Framework for On-Policy Self-Distillation

Yongkang Yang, Zhezheng Hao, Hong Zhang +8

On-policy self-distillation (OPSD) improves the reasoning abilities of LLMs by internalizing privileged context into model parameters through self-distillation. Two recent research…

cs.LG2026

Benchmarking the Residual: What Long-Horizon Evaluations Add Beyond Matched Short-Task Performance

Chao Peng, Zhiheng Lyu, Peijie Dong +2

The paper proposes a benchmark metric called the horizon residual to compare long-horizon task success against predictions from short-stage baselines, highlighting how performance…

cs.CL2026

Tencent WorkBuddy Bench: A Multi-Domain Coding-Agent Benchmark with Contamination-Resistant Task Construction

Tencent WorkBuddy Bench Team, Siqi Cai, Shaopeng Chen +35

We introduce Tencent WorkBuddy Bench, a multi-domain evaluation suite for coding agents; this report documents its construction methodology, scoring protocol, and a cross-model lea…

cs.LG2026

LEPO: Latent Reasoning Policy Optimization for Large Language Models

Yuyan Zhou, Jiarui Yu, Hande Dong +4

Recently, latent reasoning has been introduced into large language models (LLMs) to leverage rich information within a continuous space. However, without stochastic sampling, these…

cs.MA2026

Evolve as a Team: Collaborative Self-Evolution for LLM-based Multi-Agent Systems

Zhezheng Hao, Tianfu Wang, Huanshuo Dong +7

LLM-based multi-agent systems (MAS) have emerged as an effective paradigm for complex and long-horizon tasks. However, in real-world tasks, MAS often exhibit various failures durin…

cs.AI2026

Echo: Learning from Experience Data via User-Driven Refinement

Hande Dong, Xiaoyun Liang, Jiarui Yu +15

Static "human data" faces inherent limitations: it is expensive to scale and bounded by the knowledge of its creators. Continuous learning from "experience data" - interactions bet…