Groundability, Not Scale Alone: When Weak Reviewers Can Audit Strong Coding Agents

arXiv:2610.01023 · cs.SE, cs.AI, cs.CL · Submitted 2026-10-01 · Read on arXiv

cs.SE, cs.AI, cs.CL

Submitted: 2026-10-01

Updated: 2026-10-01

Terminology

• Trace — 102× in this paper · explained in 2 episodes
• Benchmark — 15× in this paper · explained in 2 episodes
• Abstention — 14× in this paper · explained in 1 episode
• Core — 14× in this paper · explained in 2 episodes
• Accuracy — 4× in this paper · explained in 1 episode
• Grounding — 4× in this paper · explained in 3 episodes
• Verifier — 4× in this paper · explained in 2 episodes
• Calibration — 3× in this paper · explained in 7 episodes
• In International Conference on Learning Representations — 3× in this paper
• International Conference on Machine Learning — 3× in this paper
• Ablation — 2× in this paper · explained in 1 episode
• Alignment — 2× in this paper · explained in 1 episode
• LLM judge — 2× in this paper · explained in 2 episodes
• LLM-as-a-Judge — 2× in this paper · explained in 3 episodes
• AI Agents — 1× in this paper · explained in 2 episodes
• Agentic Coding — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Decoupling — 1× in this paper · explained in 2 episodes
• Domain Shift — 1× in this paper · explained in 4 episodes
• Exchangeability — 1× in this paper · explained in 2 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Reward Hacking — 1× in this paper · explained in 8 episodes
• Scaling Laws — 1× in this paper · explained in 4 episodes
• Task Decomposition — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• Otter: Generating Tests from Issues to Validate SWE Patches
• CoT Red-Handed: Stress Testing Chain-of-Thought Monitoring
• Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation
• Ctrl-Z: Controlling AI Agents via Resampling
• Measuring Progress on Scalable Oversight for Large Language Models
• CodeT: Code Generation with Generated Tests
• Rethinking the Value of Agent-Generated Tests for LLM-Based Software Engineering Agents
• Dynamic Cogeneration of Bug Reproduction Test in Agentic Program Repair
• TRAIL: Trace Reasoning and Agentic Issue Localization
• Scaling Laws For Scalable Oversight
• Selective Classification for Deep Neural Networks
• Great Models Think Alike and this Undermines AI Oversight
• AI Control: Improving Safety Despite Intentional Subversion
• Speed at the Cost of Quality: How Cursor AI Increases Short-Term Velocity and Long-Term Complexity in Open-Source Projects
• AI safety via debate
• SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
• Uncovering Systematic Failures of LLMs in Verifying Code Against Natural Language Specifications
• Reliable Weak-to-Strong Monitoring of LLM Agents
• On scalable oversight with weak LLMs judging strong LLMs
• Prover-Verifier Games improve legibility of LLM outputs

Related papers

• Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
• GitSkills: A Dataset of Agent Skills on GitHub
• SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces
• PackMonitor: Enabling Zero Package Hallucinations Through Decoding-Time Monitoring
• IntentCoding: Amplifying User Intent in Code Generation
• Incentives and Outcomes in Bug Bounties