7arXiv cs.CL (Computation and Language)·
Frontis-MA1: 35B meta-evolution agent for recursive self-improvement in machine learning engineering
Researchers introduce OpenMLE, an open full-stack system for recursive self-improvement (RSI) research in machine learning engineering, and post-train Frontis-MA1 (35B) as a meta-evolution agent on top of it. The system uses four atomic program-evolution operators (Draft, Improve, Debug, Crossover) trained via execution-grounded SFT and RL, then composed into long-horizon search. On MLE-Bench Lite under a constrained single-GPU budget, Frontis-MA1 improves Medal Average from 39.39% to 71.21% with OpenMLE-Evo-Max, reportedly exceeding GPT-5.5 + Codex and approaching GPT-5.6 Sol and the 2.8T Kimi K3. Model weights and the full OpenMLE stack are released publicly, targeting reproducible RSI research.
Related guides (4)
Open Weights ProgressTopic guide
Open Weights Progress: How Free AI Models Caught Up to the Frontier
Read asBeginner
Related events (8)
MetaEvolve framework trains LLMs to self-evolve via meta-skill reinforcement learning
Researchers introduce MetaEvolve, a framework that cultivates 'meta-skills' such as self-reflection and multi-round refinement in LLMs through a data synthesis pipeline and evolution-aware reinforcement learning. Grounded in coding tasks where program execution provides continuous reward signals, the system trains on evolution trajectories containing programs, fitness scores, and attempt histories. MetaEvolve outperforms the strongest baseline by 10.01% on in-distribution coding benchmarks and 24.12% on out-of-distribution tasks, with a 46.9% relative improvement on open-ended algorithm optimization problems outside the training domain. The work is motivated by AlphaEvolve-style test-time scaling and aims to produce generalizable meta-skills transferable to domains with sparse training signals.
MLEvolve: Self-evolving multi-agent framework for automated ML algorithm discovery
MLEvolve is a new LLM-based multi-agent framework for end-to-end machine learning algorithm discovery, addressing limitations of existing MLE agents including information isolation and memoryless search. The system introduces Progressive MCGS (a graph-extended tree search), Retrospective Memory for experience accumulation, and decoupled strategic planning from code generation. Evaluated on MLE-Bench, it achieves state-of-the-art medal and valid submission rates within a 12-hour budget, and also outperforms AlphaEvolve on mathematical algorithm optimization tasks.
MindForge pipeline fine-tunes small models for whole-life-cycle software engineering via source-free program synthesis
MindForge is an automated pipeline that converts open-source command-line programs into source-free training environments exposing only compiled executables and documentation, enabling training data generation for from-scratch program synthesis. Using GLM-5.2 as a teacher agent, the authors fine-tune Qwen3.6-27B on synthesized trajectories, raising its ProgramBench pass rate from 37.98% to 49.51% and achieving gains across seven held-out benchmarks including SWE-bench Verified (+5.04) and RepoZero-C2Rust (+31.00). The work addresses a gap in coding agent training infrastructure by spanning the full software engineering life cycle rather than single-phase tasks. The result is notable for achieving frontier-comparable performance on a 27B model through targeted data curation.
Mach-Mind-4-Flash: 35B MoE agentic model matching 100B-class performance via post-training optimization
Mach-Mind-4-Flash is a 35B-parameter Mixture-of-Experts model with only 3B activated parameters that achieves performance comparable to 100B-class models through post-training techniques alone. The pipeline combines a unified RL/OPD training infrastructure with multi-teacher scheduling, parallel domain-specific RL experts fused via Multi-Teacher On-Policy Distillation (MOPD), and Hybrid Median-length Policy Optimization (HMPO) which compresses reasoning chains 19-46% with minimal accuracy loss. Benchmark results include 92.70 on AIME'26, 82.82 on IFBench, and 75.80 on BFCL-v4, claiming to lead or match models 10-30x its activated size at a fraction of inference cost. The work is notable for demonstrating that post-training optimization can close large gaps in activated parameter count for agentic tasks.
LLM-guided MAP-Elites evolution improves medical decision pipelines at inference time
Researchers propose using LLM-guided MAP-Elites evolutionary search as an inference-time alternative to fine-tuning for adapting LLMs to clinical workflows, formulating triage, consultation, and image classification as evolutionary searches over executable artifacts. Across three medical settings, evolved programs substantially outperform manually designed baselines: triage accuracy improves from 77.3% to 87.1% and emergency recall from 0.60 to 0.97, with gains also shown on MIMIC-ESI, iCRAFTMD, and PneumoniaMNIST. The approach works across Llama-3, Qwen-3.5, and Gemma-4 backbones and produces interpretable program-level mechanisms rather than superficial prompt changes.
EvoPolicyGym benchmark evaluates autonomous policy evolution by LLM agents in RL environments
A new arXiv preprint introduces EvoPolicyGym, a benchmark for evaluating how LLM-based agents iteratively improve executable policies in compact interactive RL environments under a fixed interaction budget. The benchmark provides trajectory-level diagnostics beyond aggregate scores, distinguishing how agents allocate budget and convert feedback into parametric tuning. GPT-5.5 achieves the strongest aggregate rank score and top-two performance across all 16 environments. The work targets a gap in agent evaluation where iterative policy refinement is conflated with open-ended software engineering progress.
MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering
OpenAI introduces MLE-bench, a benchmark designed to measure AI agent performance on machine learning engineering tasks. The benchmark draws from Kaggle competitions to evaluate agents on realistic ML engineering workflows. Initial results show that current agents, including those powered by o1-preview, achieve competitive performance on a subset of tasks but fall well short of top human competitors. The benchmark is intended to track progress in agentic ML capabilities over time.
RSIBench-Data: Benchmark for LLM Agents as Data-Centric Researchers in Recursive Self-Improvement
RSIBench-Data is a new benchmark that isolates the data-centric research capabilities of LLM agents within a fixed post-training stack, testing whether agents can autonomously diagnose capability gaps and revise training-data strategies to improve a target model. Four frontier agents are evaluated across six benchmarks spanning software engineering, math, and scientific QA. Agents improve on their first valid attempt in 58% of settings, but 78% of runs that continue after a peak score end lower, indicating inconsistent self-improvement. The benchmark is open-sourced and provides a controlled testbed for measuring progress toward recursive self-improvement.