Coding agents exhibit action bias by proposing undesirable changes on already-fixed issues 35-65% of the time, and explicit reproduction instructions only partially mitigate this while creating new abstention errors.
Evaluating agents
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5verdicts
UNVERDICTED 5representative citing papers
ZORO integrates rules directly into AI coding workflows by enriching plans, enforcing compliance with proof requirements, and evolving rules via user feedback, resulting in better rule adherence and shifts in user behavior.
A 1650-session factorial study found no measurable impact from config file size, instruction position, architecture, or conflicts on coding agent adherence, though compliance declined within sessions.
Compact Gene representations of experience outperform documentation-oriented Skill packages for test-time control and iterative evolution in code-solving tasks, with measured gains on CritPt from 9.1% to 18.57% and 17.7% to 27.14%.
The authors propose field-scoped epistemic grounding documents that override user prompts with non-negotiable validity rules for AI-assisted scientific software development.
citing papers explorer
-
Coding Agents Don't Know When to Act
Coding agents exhibit action bias by proposing undesirable changes on already-fixed issues 35-65% of the time, and explicit reproduction instructions only partially mitigate this while creating new abstention errors.
-
ZORO: Active Rules for Reliable Vibe Coding
ZORO integrates rules directly into AI coding workflows by enriching plans, enforcing compliance with proof requirements, and evolving rules via user feedback, resulting in better rule adherence and shifts in user behavior.
-
Instruction Adherence in Coding Agent Configuration Files: A Factorial Study of Four File-Structure Variables
A 1650-session factorial study found no measurable impact from config file size, instruction position, architecture, or conflicts on coding agent adherence, though compliance declined within sessions.
-
From Procedural Skills to Strategy Genes: Towards Experience-Driven Test-Time Evolution
Compact Gene representations of experience outperform documentation-oriented Skill packages for test-time control and iterative evolution in code-solving tasks, with measured gains on CritPt from 9.1% to 18.57% and 17.7% to 27.14%.
-
Agentic AI-assisted coding offers a unique opportunity to instill epistemic grounding during software development
The authors propose field-scoped epistemic grounding documents that override user prompts with non-negotiable validity rules for AI-assisted scientific software development.