Liu Yang, Zongmin Yu
We lifted 5 functions out of this paper's own repositories and ran 5 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| scaling-group/eve | canonical | 5 of 5 |
| Function | Status | Where it lives |
|---|---|---|
| build_run_id | Ran | scaling-group/eve/src/scaling_evolve/algorithms/eve/runner.py code served (permissive licence) · get_code("9e06c38b1cf071ff") |
| build_run_root | Ran | scaling-group/eve/src/scaling_evolve/algorithms/eve/runner.py code served (permissive licence) · get_code("380c2bbb70dd9993") |
| read_required_prompt_text | Ran | scaling-group/eve/src/scaling_evolve/algorithms/eve/prompt_assets.py code served (permissive licence) · get_code("02fb0093893ff2c6") |
| scalar | Ran | scaling-group/eve/src/scaling_evolve/algorithms/eve/populations/score.py code served (permissive licence) · get_code("dbd282cfae3f760a") |
| score_block_lines | Ran | scaling-group/eve/src/scaling_evolve/algorithms/eve/populations/score.py code served (permissive licence) · get_code("9140778c32df77ad") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
We introduce the Evolving Ensemble of Agents (EvE), a decentralized framework that organizes existing, highly capable coding agents into a live, co-evolving system for algorithmic discovery. Rather than reinventing the wheel within the "LLMs as optimizers" paradigm, EvE fixes the base agent substrate and focuses entirely on evolving the cumulative guidance and skills that dictate agent behaviors. By maintaining two co-evolving populations, namely functional code solvers and agent guidance states, the system evaluates agents through a synchronous race, updating their empirical Elo ratings based on the marginal gains they contribute to the current solver state. When applied to a research bottleneck in In-Context Operator Networks (ICON), EvE autonomously discovered a robust rescale-then-interpolate mechanism that enables reliable examplecount generalization. Crucially, controlled ablations reveal the absolute necessity of stage-dependent agent adaptation to navigate the shifting search landscapes of complex codebases. Compared to variants driven by a fixed initial agent or even a frozen "best-evolved" agent, EvE uniquely avoids phase mismatch, demonstrating that organizing agents into a selfrevising ensemble is the fundamental driver for breaking through static performance ceilings.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2605.09018")
get_code_for_paper("2605.09018")
have("2605.09018")
Connect an agent — have() is free.