Prince Kumar, Rudra Murthy, Riyaz Bhat, Danish Contractor · May 23, 2025 · Citations: 0
DemonstrationsMathCoding
We evaluate our method on 12 publicly available benchmarks spanning instruction-following, mathematical reasoning, and commonsense reasoning, across six base models.
Our results show that models trained with pseudo-code follow instructions more reliably, achieving relative gains of 8-21\% on instruction following benchmarks, while largely preserving and in some cases improving performance on…
Wenjie Lin, Jin Wei-Kocsis, Jiansong Zhang, Byung-Cheol Min, Dongming Gan, Paul Asunda · May 20, 2025 · Citations: 0
DemonstrationsGeneral
Inspired by human metacognitive learning and creative problem-solving, we address this limitation by exploring a fundamental question: Can LLMs be empowered with metacognitive capabilities to reason, reflect, and create, thereby enhancing…
We propose a more challenging robotic benchmark task and evaluate our framework on the existing benchmark and the novel task.
Yanheng He, Jiahe Jin, Pengfei Liu · May 20, 2025 · Citations: 0
DemonstrationsCoding
We introduce PC Agent-E, an efficient agent training framework that significantly reduces reliance on large-scale human demonstrations.
Trained on these enriched trajectories, our PC Agent-E model achieved a remarkable 141 relative improvement, and even surpassed the Claude 3.7 Sonnet by 10% in relative terms on WindowsAgentArena-V2, an improved benchmark we also released.
Jun Liu, Zhenglun Kong, Peiyan Dong, Changdi Yang, Tianqi Li, Hao Tang · May 20, 2025 · Citations: 0
DemonstrationsSimulation EnvGeneral
Large language models (LLMs) exhibit strong capabilities as decision-making agents by interleaving reasoning and actions, as seen in ReAct-style frameworks.
We propose Structured Agent Distillation, a framework that compresses large LLM-based agents into smaller student models while preserving both reasoning fidelity and action consistency.
Ruize Zhang, Sirui Xiang, Zelai Xu, Feng Gao, Shilong Ji, Wenhao Tang · May 7, 2025 · Citations: 0
DemonstrationsAutomatic MetricsGeneral
The task is turn-based, multi-agent, and physically grounded, posing significant challenges due to its long-horizon dependencies, tight inter-agent coupling, and the underactuated dynamics of quadrotors.
Existing techniques are either reward-based (training a reward model on preference pairs and optimizing with reinforcement learning) or reward-free (directly fine-tuning on ranked outputs).
Recent research shows that well-tuned reward-based pipelines remain the most robust, and single-response demonstrations can outperform pairwise preference data.
We provide a comprehensive suite of tasks ranging from single-drone drills to multi-drone cooperative and competitive tasks, accompanied by baseline evaluations of representative reinforcement learning (RL), multi-agent reinforcement…
Simulation results show that on-policy RL methods outperform off-policy methods in single-agent tasks, but both approaches struggle in complex tasks that combine motion control and strategic play.
We propose CowPilot, a framework supporting autonomous as well as human-agent collaborative web navigation, and evaluation across task success and task efficiency.
We conducted case studies on five common websites and found that the human-agent collaborative mode achieves the highest success rate of 95% while requiring humans to perform only 15.2% of the total steps.
In this work we present a framework for robots to continually learn tasks and visuo-motor skills and query for novel skills via dialog interactions with human users.
Moreover, with our IRB approved human-subjects study we demonstrate that our dialog based continual learning framework allows users to teach robots cooking skills successfully (100%) while spending a higher ratio of time on finishing an…
