An LLM agent with Rocq backend automatically builds a verified RISC-V RV32I interpreter (1859 lines Rocq, 2848 lines extracted C++) that passes 265 tests and 12-hour fuzzing, while a Dafny backend fails.
The FM Agent, February 2026.https://arxiv.org/abs/2510.26144
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
years
2026 13roles
dataset 1polarities
use dataset 1representative citing papers
Evolutionary coding agents achieve most benchmark gains through a small subset of edit types and by cycling previously deleted code lines rather than developing new algorithmic structures.
Arbor combines a coordinator, executors, and a hypothesis tree to enable cumulative autonomous research, outperforming Codex and Claude Code by over 2.5x on six real tasks and reaching 86.36% Any Medal on MLE-Bench Lite.
DrugSAGE accumulates cross-task memory of skills, statistical evidence, and recurring errors to let LLM agents achieve top-ranked performance on molecular property prediction tasks with reduced or zero test-time search.
AIBuildAI uses a manager agent and three LLM sub-agents to fully automate AI model development and achieves a 63.1% medal rate on MLE-Bench, matching experienced human engineers.
TREX automates the LLM training lifecycle via collaborative agents and tree-based exploration, delivering consistent performance gains across 10 real-world fine-tuning tasks in FT-Bench.
AIRA₂ improves AI research agents via asynchronous multi-GPU workers, hidden consistent evaluation, and interactive ReAct agents, reaching 81.5-83.1% percentile rank on MLE-bench-30 and exceeding human SOTA on 6 of 20 AIRS-Bench tasks.
Gome reaches 35.1% any-medal rate on MLE-Bench by mapping reasoning to gradient-based updates, outperforming tree search once models are sufficiently capable.
A hierarchical multi-agent system with File-as-Bus durable state beats matched baselines on PaperBench and MLE-Bench Lite, and ablations show project-state continuity drives later-round gains.
EurekAgent achieves new state-of-the-art results on mathematics, kernel engineering, and machine learning tasks by engineering agent environments for autonomous scientific discovery, including a 26-circle packing result at under $11 API cost.
AIBuildAI-2 introduces a knowledge-enhanced agent with a hierarchical evolving external knowledge base that dynamically loads relevant AI development expertise, achieving first place on MLE-Bench at 70.7% medal rate.
AceGRPO trains 30B-parameter LLM agents to achieve 100% valid submissions and competitive performance on MLE-Bench-Lite through evolving data buffers and adaptive task sampling.
MLEvolve is a self-evolving multi-agent LLM system with Progressive MCGS, Retrospective Memory, and adaptive coding modes that reports SOTA medal and submission rates on MLE-Bench under a 12-hour budget while outperforming AlphaEvolve on math tasks.
citing papers explorer
-
Trustworthy Software Project Generation : a Case Study with an Interactive Theorem Prover
An LLM agent with Rocq backend automatically builds a verified RISC-V RV32I interpreter (1859 lines Rocq, 2848 lines extracted C++) that passes 265 tests and 12-hour fuzzing, while a Dafny backend fails.
-
What Do Evolutionary Coding Agents Evolve?
Evolutionary coding agents achieve most benchmark gains through a small subset of edit types and by cycling previously deleted code lines rather than developing new algorithmic structures.
-
Toward Generalist Autonomous Research via Hypothesis-Tree Refinement
Arbor combines a coordinator, executors, and a hypothesis tree to enable cumulative autonomous research, outperforming Codex and Claude Code by over 2.5x on six real tasks and reaching 86.36% Any Medal on MLE-Bench Lite.
-
DrugSAGE:Self-evolving Agent Experience for Efficient State-of-the-Art Drug Discovery
DrugSAGE accumulates cross-task memory of skills, statistical evidence, and recurring errors to let LLM agents achieve top-ranked performance on molecular property prediction tasks with reduced or zero test-time search.
-
AIBuildAI: An AI Agent for Automatically Building AI Models
AIBuildAI uses a manager agent and three LLM sub-agents to fully automate AI model development and achieves a 63.1% medal rate on MLE-Bench, matching experienced human engineers.
-
TREX: Automating LLM Fine-tuning via Agent-Driven Tree-based Exploration
TREX automates the LLM training lifecycle via collaborative agents and tree-based exploration, delivering consistent performance gains across 10 real-world fine-tuning tasks in FT-Bench.
-
AIRA_2: Overcoming Bottlenecks in AI Research Agents
AIRA₂ improves AI research agents via asynchronous multi-GPU workers, hidden consistent evaluation, and interactive ReAct agents, reaching 81.5-83.1% percentile rank on MLE-bench-30 and exceeding human SOTA on 6 of 20 AIRS-Bench tasks.
-
Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search
Gome reaches 35.1% any-medal rate on MLE-Bench by mapping reasoning to gradient-based updates, outperforming tree search once models are sufficiently capable.
-
Toward Autonomous Long-Horizon Engineering for ML Research
A hierarchical multi-agent system with File-as-Bus durable state beats matched baselines on PaperBench and MLE-Bench Lite, and ablations show project-state continuity drives later-round gains.
-
EurekAgent: Agent Environment Engineering is All You Need For Autonomous Scientific Discovery
EurekAgent achieves new state-of-the-art results on mathematics, kernel engineering, and machine learning tasks by engineering agent environments for autonomous scientific discovery, including a 26-circle packing result at under $11 API cost.
-
AIBuildAI-2: A Knowledge-Enhanced Agent for Automatically Building AI Models
AIBuildAI-2 introduces a knowledge-enhanced agent with a hierarchical evolving external knowledge base that dynamically loads relevant AI development expertise, achieving first place on MLE-Bench at 70.7% medal rate.
-
AceGRPO: Adaptive Curriculum Enhanced Group Relative Policy Optimization for Autonomous Machine Learning Engineering
AceGRPO trains 30B-parameter LLM agents to achieve 100% valid submissions and competitive performance on MLE-Bench-Lite through evolving data buffers and adaptive task sampling.
-
MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery
MLEvolve is a self-evolving multi-agent LLM system with Progressive MCGS, Retrospective Memory, and adaptive coding modes that reports SOTA medal and submission rates on MLE-Bench under a 12-hour budget while outperforming AlphaEvolve on math tasks.