13 papers
CoCoBench: A Cooperative Coordination Benchmark for Embodied Multi-Agent Task Planning
Yang Chen, Ye-Xin Xie, Lirong Che +8
Agent systems powered by multimodal large language models (MLLMs) have advanced rapidly in recent years, yet existing embodied-agent benchmarks still lack fine-grained diagnostics…
CoRT: Counterfactual Replay for Token-Level Rubric-Guided Policy Optimization
Bo-Wen Zhang, Junwei He, Wen Wang +5
Rubric-based reinforcement learning enriches language model training by evaluating model outputs against explicit criteria. Yet in GRPO-style pipelines, these structured judgments…
CAST: Game Solvers as Turn-Level Teachers for LLM Agents
Yu Wang, Yi-Kai Zhang, Wentao Shi +8
Training large language models (LLMs) to act in long-horizon games is a promising step toward generalist decision-making, yet reinforcement learning with verifiable rewards (RLVR)…
Stabilizing Recurrent Dynamics for Test-Time Scalable Latent Reasoning in Looped Language Models
Xiao-Wen Yang, Ziyu Han, Xi-Hua Zhang +4
Looped Language Models (LoopLMs) enable efficient latent reasoning through depth recurrence, yet exhibit unreliable test-time scaling behavior: performance often peaks at a certain…
Aligning Agents via Planning: A Benchmark for Trajectory-Level Reward Modeling
Jiaxuan Wang, Yulan Hu, Wenjin Yang +3
In classical Reinforcement Learning from Human Feedback (RLHF), Reward Models (RMs) serve as the fundamental signal provider for model alignment. As Large Language Models evolve in…
Revisiting the Travel Planning Capabilities of Large Language Models
Bo-Wen Zhang, Jin Ye, Peng-Yu Hua +4
Travel planning serves as a critical task for long-horizon reasoning, exposing significant deficits in LLMs. However, existing benchmarks and evaluations primarily assess final pla…
Programmatic Context Augmentation for LLM-based Symbolic Regression
Hao Liu, Xiao-Wen Yang, Atharva Sehgal +4
Symbolic regression (SR), the task of discovering mathematical expressions that best describe a given dataset, remains a fundamental challenge in scientific discovery. Traditional…
Lifting Traces to Logic: Programmatic Skill Induction with Neuro-Symbolic Learning for Long-Horizon Agentic Tasks
Jie-Jing Shao, Haiyan Yin, Yueming Lyu +5
Foundation model-driven agents often struggle with long-horizon planning due to the transient nature of purely prompting-based reasoning. While existing skill induction methods mit…
Aligning Progress and Feasibility: A Neuro-Symbolic Dual Memory Framework for Long-Horizon LLM Agents
Bin Wen, Ruoxuan Zhang, Yang Chen +2
Large language models (LLMs) have demonstrated strong potential in long-horizon decision-making tasks, such as embodied manipulation and web interaction. However, agents frequently…
Thinking with Tables: Enhancing Multi-Modal Tabular Understanding via Neuro-Symbolic Reasoning
Kun-Yang Yu, Zhi Zhou, Shi-Yu Tian +6
Multimodal Large Language Models (MLLMs) have demonstrated remarkable reasoning capabilities across modalities such as images and text. However, tabular data, despite being a criti…
Hindsight Credit Assignment for Long-Horizon LLM Agents
Hui-Ze Tan, Xiao-Wen Yang, Hao Chen +7
Large Language Model (LLM) agents often face significant credit assignment challenges in long-horizon, multi-step tasks due to sparse rewards. Existing value-free methods, such as…
Pianist Transformer: Towards Expressive Piano Performance Rendering via Scalable Self-Supervised Pre-Training
Hong-Jie You, Jie-Jing Shao, Xiao-Wen Yang +3
Existing methods for expressive music performance rendering, a conditional generation task that aims to generate a human-like performance from a symbolic score, rely on supervised…
D3: Diversity, Difficulty, and Dependability-Aware Data Selection for Sample-Efficient LLM Instruction Tuning
Jia Zhang, Chen-Xi Zhang, Yao Liu +5
Recent advancements in instruction tuning for large language models (LLMs) suggest that a small, high-quality dataset can significantly equip LLMs with instruction-following capabi…