Proof pending. Core topic summary fields are still materializing.
AI planning is evolving through innovative approaches that enhance the efficiency and quality of plan generation. Recent advancements focus on leveraging generative models and hierarchical task networks to produce high-quality plans in less time. Techniques such as self-improvement of models, learning transition dynamics, and utilizing large language models for heuristic generation are proving effective. These developments are crucial for builders, as they enable the creation of more robust, adaptable planning systems that can operate in complex, dynamic environments. The ability to generate optimal plans quickly and accurately is essential for applications ranging from robotics to automated decision-making, making these advancements significant for the future of AI planning.
Topic-specific paper and score movement from the daily diff ledger.
HTN planning is a variation of classical planning where, instead of searching for a linear sequence of actions, an algorithm decomposes higher-level tasks using a method library until only executable ...
Generative models trained on synthetic plan data are a promising approach to generalized planning. Recent work has focused on finding any valid plan, rather than a high-quality solution. We address th...
To safely interact with humans, AI agents must both know our norms and consider them during planning. However, such norm-guided planning has been less explored, only within communities of artificial a...
Generalized planning studies the construction of solution strategies that generalize across families of planning problems sharing a common domain model, formally defined by a transition function $γ: S...
Epistemic planning extends (multi-agent) automated planning by making agents' knowledge and beliefs first-class aspects of the planning formalism. One of the most well-known frameworks for epistemic p...
Autonomous agents require some form of goal and plan recognition to interact in multiagent settings. Unfortunately, all existing goal recognition datasets suffer from a systematical bias induced by th...
Active inference, a neurally-inspired model for inferring actions based on the free energy principle (FEP), has been proposed as a unifying framework for understanding perception, action, and learning...
Large Language Models (LLMs) have enabled automated heuristic design (AHD) for combinatorial optimization problems (COPs), but existing frameworks' reliance on fixed evolutionary rules and static prom...
Efficient construction of models capturing the preconditions and effects of actions is essential for applying AI planning in real-world domains. Extensive prior work has explored learning such models ...
Plans often change due to changes in the situation or our understanding of the situation. Sometimes, a feasible plan may not even exist, and identifying such infeasibilities is useful to determine whe...
Freshness
Canonical route: /topics
Agent Handoff
Canonical ID ai-planning | Route /topic/ai-planning
REST example
curl https://sciencetostartup.com/api/v1/agent-handoff/topic/ai-planningMCP example
{
"tool": "search_papers",
"arguments": {
"query": "AI Planning",
"cluster": "AI Planning"
}
}source_context
{
"surface": "topic",
"mode": "topic",
"query": "AI Planning",
"normalized_query": "ai-planning",
"route": "/topic/ai-planning",
"paper_ref": null,
"topic_slug": "ai-planning",
"benchmark_ref": null,
"dataset_ref": null
}Use This Via API or MCP
Topic pages bundle paper counts, viability trends, author concentration, and top questions into one canonical surface your agents can reference before they open Signal Canvas or create a workspace.