AgentPRO: Coordinating Compiler Optimizations for LLM Agent Workflows
cs.SE
Submitted: 2026-10-31
Updated: 2026-10-31
Code: https://github.com/StonyBrookNLP/appworld
Terminology
Sources
- SkVM: Revisiting Language VM for Skills across Heterogenous LLMs and Harnesses
- TraceCompiler: Skill-Guided Mining and Compilation of LLM Agent Traces into Mostly Deterministic Workflows
- SkillReducer: Optimizing LLM Agent Skills for Token Efficiency
- ACON: Optimizing Context Compression for Long-horizon LLM Agents
- The Complexity Trap: Simple Observation Masking Is as Efficient as LLM Summarization for Agent Context Management
- Adapting Context Compression for Long-Horizon Agents with Counterfactual Continuations
- Beyond Token Savings: A Systematic Study of Context Compression in LLM Agents
- An LLM-Tool Compiler for Fused Parallel Function Calling
- StateComp: Learning When to Compress History in Long Horizon Agents
- Reducing Cost of LLM Agents with Trajectory Reduction
- ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models
- SkillSmith: Compiling Agent Skills into Boundary-Guided Runtime Interfaces
- AgentFold: Long-Horizon Web Agents with Proactive Context Management
- Agentic Plan Caching: Test-Time Memory for Fast and Cost-Efficient LLM Agents
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