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.
Set up three distinct, unseen 2D grid environments (e.g., `env_A.json`, `env_B.json`, `env_C.json`) with different layouts, object placements, and obstacles. For a given task instruction, run the BeeAgent in each environment. Evaluate its success rate, action efficiency, and adaptability across these environments. Additionally, analyze the agent's memory interactions (retrieval frequency, relevance of retrieved memories) to understand how the pgvector-backed memory contributes to its adaptive behavior.
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 rubric, target behavior, and pass-fail criteria as the baseline for evaluation.
Adjust fixtures, mocks, and thresholds to the system under test instead of weakening the assertions.
Make sure the prompt catches regressions instead of just mirroring the happy-path examples.
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 Adaptive BeeAgent for Multimodal Visual-Language Tasks in Simulated Environments with Gemini 2.5 Pro and pgvector
This challenge involves creating an intelligent agent using the BeeAgent framework that can learn and adapt its behavior to perform complex visual-language tasks across varied simulated environments. Drawing inspiration from research on 'Automated Environments for Measuring Cross-Environment Agent Learning' (AutoEnv) and 'Collaborative Visual-Language Reasoning and Navigation via a Multimodal World Model' (UNeMo), the agent will demonstrate robust reasoning and adaptability. The agent, powered by Gemini 2.5 Pro's advanced multimodal capabilities, will interpret visual cues from simulated scenes, understand natural language instructions, and execute actions (e.g., navigation, object manipulation). A key aspect is the agent's ability to adapt its strategies to new layouts or minor rule changes in unseen environments, with its memories and learned patterns persisted in a Postgres database utilizing the `pgvector` extension for efficient semantic retrieval. This challenge will push the boundaries of multimodal understanding, adaptive agent design, and persistent memory for agents.
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.