Eliciting and Mitigating Specification Satisficing in Coding Agents
cs.SE, cs.AI, cs.CL
Submitted: 2026-11-12
Updated: 2026-11-12
Code: https://github.com/python-attrs/cattrs
Terminology
Sources
- Eliciting Secret Knowledge from Language Models
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
- SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?
- Chain-of-Verification Reduces Hallucination in Large Language Models
- Gemma 4 Technical Report
- Large Language Models Cannot Self-Correct Reasoning Yet
- DeepSWE: Measuring Frontier Coding Agents on Original, Long-Horizon Engineering Tasks
- Doc2Feat-Bench: Evaluating Documentation-Driven Feature Addition
- Training LLMs for Honesty via Confessions
- Agentic Uncertainty Reveals Agentic Overconfidence
- Large Language Models Understand and Can be Enhanced by Emotional Stimuli
- An Empirical Study on Failures in Automated Issue Solving
- Self-Refine: Iterative Refinement with Self-Feedback
- Auditing language models for hidden objectives
- When Agents Commit Too Soon: Diagnosing Premature Commitment in LLM Agents
- Muse Glimmer 30B: An On-Device Agentic Model
- SpecRover: Code Intent Extraction via LLMs
- Reflexion: Language Agents with Verbal Reinforcement Learning
- Large Language Models are Better Reasoners with Self-Verification
- Benchmarking and Studying the LLM-based Agent System in End-to-End Software Development
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