16 papers
SCAD: Structured Credit Assignment and Distillation for Long-Horizon Agents
Shangyang Wu, Shuai Zhao, Ziyue Zhu +3
Training long-horizon agents to solve complex tasks requires effective supervision over extended interaction sequences. However, sparse terminal rewards obscure intermediate contri…
CHAIN: Calibrated LLM Forecasting via Causal-Temporal Hypergraph Inference
Wenjin Liu, Chenxi Wang, Yue Lu +2
Large language models have achieved significant progress in event forecasting, yet their probability outputs exhibit systematic calibration bias that varies heterogeneously across…
TIEM: Temporal Integration of Hypergraph Evidence and Skill Memory for Event-Driven Financial Forecasting
Wenjin Liu, Shen Pang, Chenxi Wang +6
Event-driven catalyst-outcome forecasting increasingly uses retrieval- and memory-augmented large language model agents for prediction. However, training-data contamination and tem…
CataOPD: Catalytic On-Policy Distillation for Large Language Model Reasoning
Wenjin Liu, Chenxi Wang, Jiapu Wang +3
Reinforcement learning (RL) and on-policy distillation (OPD) are two representative paradigms for improving large language model reasoning. However, when no correct trajectory is s…
AdaPilot: Towards Scene-Adaptive Policy Learning for Cross-Generator Text-to-Image Quality Optimization
Wenjin Liu, Fayuan Ke, Yue Lu +3
Existing methods for improving text-to-image generation quality have progressed from generator fine-tuning and prompt optimization to reinforcement learning with multi-turn visual…
MMDynOpt-Agent: Dynamic Optimization for Multimodal Large Language Model Reasoning via Reinforcement Learning
Wenjin Liu, Haoran Luo, Fayuan Ke +5
Recently, multimodal large language models (MLLMs) have demonstrated strong potential in visual understanding and complex reasoning tasks. However, existing methods often struggle…
PowerAtlas: Feasibility-Aware Language Models for Electricity-Computing Co-Scheduling
Kaiwen Jiang, Siya Xu, Ziyue Zhu +4
Electricity-computing co-scheduling (ECCS) decides where and when computing tasks run together with how generators are dispatched, because task placement changes nodal demand while…
SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning
Jinyang Wu, Shuo Yang, Zhengxi Lu +8
Large language models are increasingly trained as interactive agents for long-horizon tasks involving multi-turn interaction, tool use, and environment feedback. Outcome-based rein…
OPID: On-Policy Skill Distillation for Agentic Reinforcement Learning
Shuo Yang, Jinyang Wu, Zhengxi Lu +8
Outcome-based reinforcement learning provides a stable optimization backbone for language agents, but its sparse trajectory-level rewards provide little guidance on which intermedi…
Maestro: Reinforcement Learning to Orchestrate Hierarchical Model-Skill Ensembles
Jinyang Wu, Guocheng Zhai, Ruihan Jin +7
The proliferation of large language models (LLMs) and modular skills has endowed autonomous agents with increasingly powerful capabilities. Existing frameworks typically rely on mo…
SkillFlow: Flow-Driven Recursive Skill Evolution for Agentic Orchestration
Mingda Zhang, Tiesunlong Shen, Haoran Luo +4
In recent years, a variety of powerful LLM-based agentic systems have been applied to automate complex tasks through task orchestration. However, existing orchestration methods sti…
BenchBench: Benchmarking Automated Benchmark Generation
Yandan Zheng, Haoran Luo, Zhenghong Lin +2
Benchmarks are the de facto standard for tracking progress in large language models (LLMs), yet static test sets can rapidly saturate, become vulnerable to contamination, and are c…
OrchMAS: Orchestrated Reasoning with Multi Collaborative Heterogeneous Scientific Expert Structured Agents
Yichao Feng, Haoran Luo, Zhenghong Lin +4
Multi-agent large language model frameworks are promising for complex multi step reasoning, yet existing systems remain weak for scientific and knowledge intensive domains due to s…
OdysseyArena: Benchmarking Large Language Models For Long-Horizon, Active and Inductive Interactions
Hang Yan, Fangzhi Xu, Qiushi Sun +14
The advancement of Large Language Models (LLMs) has catalyzed the development of autonomous agents capable of navigating complex environments. However, existing evaluations primari…
FlowSteer: Towards Agents Designing Agentic Workflows via Reinforced Progressive Canvas Editing
Mingda Zhang, Wenjin Liu, Tiesunlong Shen +5
In recent years, agentic workflows have been widely applied to solve complex human tasks. However, existing workflow construction still faces key challenges, including human-depend…
SSL: Sweet Spot Learning for Differentiated Guidance in Agentic Optimization
Jinyang Wu, Changpeng Yang, Yuhao Shen +9
Reinforcement learning with verifiable rewards has emerged as a powerful paradigm for training intelligent agents. However, existing methods typically employ binary rewards that fa…