FlowPlan: Reducing the Token Cost of Coding Agents with Abstraction-Guided Planning and Verification
cs.SE
Submitted: 2026-11-09
Updated: 2026-11-09
Code: https://github.com/MelikaSepidband/FlowPlan
Project page: https://colbymchenry.github.io/codegraph
Terminology
Sources
- Learning to Represent Programs with Graphs
- Long Live the Librarian! A Persistent Search Sub-Agent for Energy-Efficient Multi-Agent Software Engineering Systems
- SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?
- More with Less: An Empirical Study of Turn-Control Strategies for Efficient Coding Agents
- GraphCodeBERT: Pre-training Code Representations with Data Flow
- EET: Experience-Driven Early Termination for Cost-Efficient Software Engineering Agents
- ACON: Optimizing Context Compression for Long-horizon LLM Agents
- BAGEN: Are LLM Agents Budget-Aware?
- To Run or Not to Run: Analyzing the Cost-Effectiveness of Code Execution in LLM-Based Program Repair
- GraphCoder: Enhancing Repository-Level Code Completion via Code Context Graph-based Retrieval and Language Model
- Closing the Loop: Universal Repository Representation with RPG-Encoder
- LLM Agents Can See Code Repositories
- ARISE: A Repository-level Graph Representation and Toolset for Agentic Program Repair and Fault Localization
- How Should Agents See Code? Rethinking Code Representations for Agentic Software Engineering
- Scaling Long-Horizon LLM Agent via Context-Folding
- SHERLOC: Structured Diagnostic Localization for Code Repair Agents
- Reducing Cost of LLM Agents with Trajectory Reduction
- Learning Adaptive Parallel Execution for Efficient Code Localization
- OrcaLoca: An LLM Agent Framework for Software Issue Localization
Related papers
- ArkEval: Benchmarking and Evaluating Automated CodeRepair for ArkTS
- TestPrism: Rethinking Test Evaluation Beyond a Single Reference
- Mining Workflow Graphs for Black-Box Boundary Testing of Conversational LLM Agents
- Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
- GitSkills: A Dataset of Agent Skills on GitHub
- For Coding Agents, the Repository Matters