cs.SENov 12, 2026

Eliciting and Mitigating Specification Satisficing in Coding Agents

Authors: Ruixin Wang, Tianyi Zhang

Organizations: Purdue University

Abstract

Coding agents often fail to meet all requirements in the task description. In some of these failures, the agent considers an implementation choice that meets a requirement, but later decides to commit to another one that does not meet the requirement for a reason it finds acceptable. We call this specification satisficing. It is challenging to identify and mitigate specification satisficing because the agent accepts such choices for its own reasons, and existing self-correction methods are biased toward them. We propose SatisFix, which guides a coding agent to report these choices and their reasons, and then check each choice against the task description. We evaluate SatisFix on DeepSWE and SWE-bench Pro with five LLMs as backbones and two different agent frameworks, and compare it with three self-correction methods. SatisFix improves the pass@1 of the base agent by an average of 5.09% on DeepSWE and 7.06% on the hard subset of SWE-bench Pro. On DeepSWE, it outperforms the best baseline by 3.98%. Our ablation study shows that both steps of SatisFix contribute to the improvement.

Figures & tables

Explore similar work

CardsList
  1. AgentSWE: Can Coding Agents Build the Agent You Actually Want?

    Oct 9, 2026Jiahao Wang, Hongjin Qian, Yuyang Hu +2Coding AgentsSoftware Engineering Agents

  2. SpecForge: Recursive Self-Improvement for Coding Agents via Behavioral Specifications

    Oct 11, 2026Yutong Cheng, Haifeng Chen, Peng Gao +1Software Engineering AgentsAgentic Code Generation

  3. Termination Lag: Coding Agents Solve Early but Stop Late

    Nov 11, 2026Musa Cim, Burak Topcu, Mahmut Taylan KandemirLLM AgentsLLM Agent Efficiency