domains / families / research / auto-paper-improvement-loop

auto-paper-improvement-loop

combined

Autonomously improve a generated paper via GPT-5.4 xhigh review → implement fixes → recompile, for 2 rounds. Use when user says \"改论文\", \"improve paper\", \"论文润色循环\", \"auto improve\", or wants to iteratively polish a generated paper. Autonomously improve a generated paper via GPT-6-Astra xhigh review → implement fixes → recompile, for 2 rounds. Use when user says \"改论文\", \"improve paper\", \"论文润色循环\", \"auto improve\", or wants to iteratively polish a generated paper.

When to use

• improve paper
• 论文润色循环
• auto improve
• iteratively polish a generated paper
• fixing theoretical inconsistencies
• softening overclaims
• adding missing content
• improving presentation

When not to use

• iterating on research
• running experiments
• collecting data
• rewriting narrative

Skill page

Conflict

Both copies describe the same two-round review→fix→recompile loop, but they disagree on the reviewer model (gpt-6-astra vs gpt-5.4) and on a core loop mechanic: the wanshuiyin copy mandates a fresh reviewer thread each round (REVIEWER_BIAS_GUARD, no codex-reply) and adds style-ref/edit-whitelist options, while the brycewang copy explicitly uses codex-reply with the saved threadId in Round 2 and adds state-persistence recovery. Crowning one would hide a real alternative procedure.