REVIEW 4 cited by
Plan-over-Graph: Towards Parallelable LLM Agent Schedule
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Large Language Models (LLMs) have demonstrated exceptional abilities in reasoning for task planning. However, challenges remain under-explored for parallel schedules. This paper introduces a novel paradigm, plan-over-graph, in which the model first decomposes a real-life textual task into executable subtasks and constructs an abstract task graph. The model then understands this task graph as input and generates a plan for parallel execution. To enhance the planning capability of complex, scalable graphs, we design an automated and controllable pipeline to generate synthetic graphs and propose a two-stage training scheme. Experimental results show that our plan-over-graph method significantly improves task performance on both API-based LLMs and trainable open-sourced LLMs. By normalizing complex tasks as graphs, our method naturally supports parallel execution, demonstrating global efficiency. The code and data are available at https://github.com/zsq259/Plan-over-Graph.
Forward citations
Cited by 4 Pith papers
-
A Two-Tier Perspective on Inference-Time Parallelism in Multi-Agent LLM Systems
A two-tier parallel execution framework for LLM multi-agent systems shows that combining replica-level and structural parallelism yields the best accuracy-latency trade-off, with diminishing returns beyond moderate settings.
-
Beyond Sequential Interaction: Benchmarking Parallel Execution and Coordination for GUI Agents
A planner–worker system that splits GUI tasks across five concurrent desktop agents reaches 46.4% success on a new 233-task benchmark, but much of the gain comes from planning rather than parallelism.
-
Graphs Meet AI Agents: Taxonomy, Progress, and Future Opportunities
A survey that groups graph-empowered AI agent research into planning, execution, memory, and multi-agent coordination, plus agents-for-graphs and applications.
-
Graph-Augmented Large Language Model Agents: Current Progress and Future Prospects
A survey that categorizes Graph-augmented LLM Agent research into planning, memory, tool management, and multi-agent design, and outlines open directions.
Discussion (0). Continue with ORCID to comment.