Operator-ready prompt for reuse, tuning, and workspace runs.
This item is set up for developers who want to inspect the original language, fork it into Workspace, and adapt the evidence model without losing the source prompt structure.
Implementation handoffs, eval setup, and prompt tuning where you need the original structure intact.
Inspect first, copy once, then fork into Workspace when you want variants, notes, and model settings attached to the same run.
Swap domain facts, examples, and any hard-coded entities for your own context.
Tighten the evidence or verification requirement if this is headed toward production.
Decide which failure mode you want to evaluate first before you branch the prompt.
This prompt already carries implementation detail, tool context, and a final-output instruction. Keep that structure intact when you tune it, or your comparison runs get noisy fast.
Open this prompt inside Workspace when you want a live iteration loop.
Copy for quick reuse, or run it in Workspace to keep prompt variants, model settings, and prompt-history changes in one place.
Structured source with 1 active lines to adapt.
Already linked to a challenge workflow.
Sign in to keep private prompt variations.
Prompt content
Original prompt text with formatting preserved for inspection and clean copy.
Design a LangGraph StateGraph that includes three nodes: 'generator', 'adversary', and 'summarizer'. Define a state that persists the current logical draft and the adversary's critiques. Use Claude 3.5 Sonnet as the default LLM.
Adaptation plan
Keep the source stable, then branch your edits in a predictable order so the next prompt run is easier to evaluate.
Preserve the role framing, objective, and reporting structure so comparison runs stay coherent.
Swap in your own domain constraints, anomaly thresholds, and examples before you branch variants.
Check whether the prompt asks for the right evidence, confidence signal, and escalation path.
Copy once for a pristine source snapshot, then move the prompt into Workspace when you want variants, run history, and side-by-side tuning without losing the original.
Prompt diagnostics
Quick signals for how structured this prompt already is and where adaptation work is likely to happen first.
This prompt is mostly narrative and instruction-driven, so you can adapt examples and output constraints first without disturbing the structure.
Build an Adversarial Reasoning Multi-Agent System with LangGraph and OpenAI o3
Inspired by recent research on Generative Adversarial Reasoners (arXiv:2512.16917), this challenge tasks you with building a sophisticated multi-agent system that utilizes adversarial reinforcement loops to improve reasoning quality. You will create a 'Generator' agent that proposes complex step-by-step solutions to logical puzzles and an 'Adversary' agent that specifically probes for logical fallacies, edge cases, and hallucinations in those steps. The system must implement a feedback loop where the Generator must refine its 'Extended Thinking' based on the Adversary's critiques. This mirrors the cutting-edge approach of using adversarial reinforcement learning to enhance LLM reasoning beyond simple zero-shot prompting. You will use LangGraph to manage the cyclical state and state-of-the-art reasoning models like OpenAI o3 or Claude 3.5 Sonnet to handle the cognitive heavy lifting.
Use the challenge page to recover the original task boundaries before you tune the prompt. That keeps your variants grounded in the same evaluation target instead of drifting into a different problem.