SPIN enforces DAG-valid plans and prefix-based stopping for LLM agents, cutting executed tasks from 1061 to 623 and tool calls from 11.81 to 6.82 per run on AssetOpsBench while raising success from 0.638 to 0.706.
Spiral: Symbolic llm planning via grounded and reflective search
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.AI 2years
2026 2representative citing papers
MCP-Cosmos combines world models with MCP agents via a bring-your-own-world-model strategy and reports gains in tool success rate and parameter accuracy on benchmark tasks.
citing papers explorer
-
SPIN: Structural LLM Planning via Iterative Navigation for Industrial Tasks
SPIN enforces DAG-valid plans and prefix-based stopping for LLM agents, cutting executed tasks from 1061 to 623 and tool calls from 11.81 to 6.82 per run on AssetOpsBench while raising success from 0.638 to 0.706.
-
MCP-Cosmos: World Model-Augmented Agents for Complex Task Execution in MCP Environments
MCP-Cosmos combines world models with MCP agents via a bring-your-own-world-model strategy and reports gains in tool success rate and parameter accuracy on benchmark tasks.