ControlScope: Workflow Revision and Reliability in LLM Agents

arXiv:2609.34313 · cs.AI, cs.CL, cs.SE · Submitted 2026-09-28 · Read on arXiv

cs.AI, cs.CL, cs.SE

Submitted: 2026-09-28

Updated: 2026-09-28

Terminology

• Trace — 4× in this paper · explained in 2 episodes
• Adaptation — 3× in this paper · explained in 1 episode
• Benchmark — 3× in this paper · explained in 2 episodes
• Verifier — 2× in this paper · explained in 2 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Adaptive Planning — 1× in this paper · explained in 1 episode
• Agent Harness — 1× in this paper · explained in 2 episodes
• Benchmarking — 1× in this paper · explained in 3 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Decoupling — 1× in this paper · explained in 2 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• Iterative Refinement — 1× in this paper · explained in 3 episodes
• Model Context Protocol — 1× in this paper
• Model Context Protocol (MCP) — 1× in this paper · explained in 8 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Task Planning — 1× in this paper · explained in 2 episodes

Sources

• Towards Reliable Code-as-Policies: A Neuro-Symbolic Framework for Embodied Task Planning
• Teaching Large Language Models to Self-Debug
• Defeating Prompt Injections by Design
• Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks
• From Tool Orchestration to Code Execution: A Study of MCP Design Choices
• An LLM Compiler for Parallel Function Calling
• Same Signal, Opposite Meaning: Direction-Informed Adaptive Learning for LLM Agents
• Code as Policies: Language Model Programs for Embodied Control
• AgentBench: Evaluating LLMs as Agents
• ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities
• Self-Refine: Iterative Refinement with Self-Feedback
• Is Bash All You Need? An Empirical Study of Tool Interfaces for Enterprise Digital Worker Agents
• Revision or Re-Solving? Decomposing Second-Pass Gains in Multi-LLM Pipelines
• One Run Is Not an Idea: The Implementation Lottery in Automated Research
• Do Agents Need to Plan Step-by-Step? Rethinking Planning Horizon in Data-Centric Tool Calling
• LLM-as-Code: Agentic Programming for Agent Harness
• Toolformer: Language Models Can Teach Themselves to Use Tools
• Reflexion: Language Agents with Verbal Reinforcement Learning
• ALFWorld: Aligning Text and Embodied Environments for Interactive Learning
• AdaPlanner: Adaptive Planning from Feedback with Language Models

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection