A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Unknown
A closed-loop long-horizon robotic planning method using equilibrium sequence modeling that more than doubles baseline success rates on long-horizon tasks.
Unknown
A decade-long review of evolving architectures and long-horizon planning in multi-agent conversational AI, synthesizing progress and open challenges.
Unknown
GraphThink uses task graphs to enhance LLM planning for long-horizon embodied tasks, with GRPO-based reward design.
Unknown
ActSWM introduces action-sensitive world models for long-horizon planning in open-world games, improving latent model-predictive control.
Unknown
The paper proposes an LLM-driven symbolic planning combined with hierarchical imitation learning framework for long-horizon deformable object assembly tasks.
Xiaowei Cai, Yunuo Cai, Bingao Chen, et al.
τ_0-VLA is a hierarchical robot foundation model that uses world-model-guided test-time computation to allocate additional inference compute for high-level subtask generation, improving long-horizon manipulation.
Bingxin Xu, Yuzhang Shang, Emilio Ferrara
BATON improves long-horizon robot manipulation by making subtasks the unit of exploration and adding transition-aware memory, boosting task success by 11.6% over SoTA.
Ziheng Qin, Yaxin Lu, Zhangyang Atlas Wang, et al.
StateM is an agent-native runtime that improves long-horizon agent performance via harness scaling, reaching 95.3% raw accuracy on Terminal-Bench 2.1 without changing model weights.
Yaxin Luo, Haobin Jiang, Jialv Zou, et al.
AutoDesign introduces a meta-harness optimization framework for long-horizon agentic design, achieving state-of-the-art paper-to-poster generation with recursive self-improvement.
Unknown
HDFlow introduces a hierarchical diffusion-flow planning framework for long-horizon robotic assembly, leveraging a structured latent space to improve task decomposition and execution.
Unknown
This paper introduces a scalable safe long-horizon planning method that uses copulas to model temporal correlations in uncertainty, providing probabilistic guarantees via conformal prediction.
Unknown
This paper presents a language-guided long-horizon manipulation framework for multistep cloth folding, combining LLM-based planning with visual perception.