arXiv AI
Jun 12
EurekAgent: Agent Environment Engineering is All You Need For Autonomous Scientific Discovery
arXiv:2606. 13662v1 Announce Type: new Abstract: LLM-based agents have shown increasing potential in automating scientific discovery.
CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery
CORAL is a framework that enables autonomous multi‑agent evolution for open‑ended discovery, replacing rigid heuristics with long‑running agents that explore, reflect, and collaborate via shared memory and asynchronous execution. It incorporates safeguards such as isolated workspaces, evaluator separation, and resource management. In experiments across mathematical, algorithmic, and systems optimization tasks, CORAL achieves 3–10 times higher improvement rates with fewer evaluations than traditional evolutionary baselines, and improves the best known score on Anthropic’s kernel engineering task from 1363 to 1103 cycles.
Related stories
arXiv AI
Sep 7
OR-Agent: Bridging Evolutionary Search and Structured Research for Automated Heuristic Design
OR-Agent is a multi‑agent research framework that automates heuristic design for optimization problems by structuring heuristic search as a tree‑based workflow with explicit hypothesis generation and systematic backtracking. It introduces a hierarchical, optimization‑inspired reflection system that uses short‑term reflections as verbal gradients, long‑term reflections as verbal momentum, and memory compression as semantic weight decay to guide research dynamics. Experiments on classical combinatorial optimization tasks and simulation‑based cooperative driving scenarios show that OR‑Agent outperforms strong evolutionary search baselines, with all code and data publicly available.
arXiv AI
Aug 5
OR-Agent: Bridging Evolutionary Search and Structured Research for Automated Algorithm Discovery
arXiv:2602. 13769v3 Announce Type: replace Abstract: Automating heuristic design in complex, experiment-driven domains requires more than iterative mutation of solution algorithms.
arXiv Machine Learning
Sep 23
Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated Reasoning
Agent0 is a fully autonomous framework that enables large language model agents to evolve without external data by using a multi‑step co‑evolution process. It pits a curriculum agent against an executor agent, both derived from the same base LLM, where the curriculum agent creates increasingly challenging tasks and the executor learns to solve them. By integrating external tools into the executor’s workflow, the system creates a self‑reinforcing cycle that continuously generates high‑quality curricula, leading to significant gains in reasoning performance—an 18% improvement on mathematical reasoning and 24% on general reasoning for the Qwen3‑8B‑Base model.
arXiv AI
Jul 29
Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering
arXiv:2607. 25090v1 Announce Type: new Abstract: Machine learning engineering (MLE) tasks require long-horizon decision making over iterative solution debugging and refinement, under expensive and feedback-driven environment interactions.
arXiv AI
Jun 9
Benchmarking Open-Ended Multi-Agent Coordination in Language Agents
arXiv:2606. 08340v1 Announce Type: new Abstract: As language models are increasingly deployed as autonomous agents, they must coordinate with others over long horizons in open-ended interactive tasks.
arXiv Computation and Language
Aug 28
MineExplorer: Evaluating Open-World Exploration of MLLM Agents in Minecraft
MineExplorer is a benchmark designed to assess the open‑world exploration abilities of multimodal large language models (MLLMs) in Minecraft. It filters out tasks that rely heavily on Minecraft‑specific knowledge, organizes tasks into ReAct‑style capabilities, and composes atomic tasks into implicit multi‑hop challenges. A multi‑agent synthesis workflow creates reliable task graphs, sandbox scenes, and rule‑based milestone evaluators, and human evaluation confirms its superiority over a single‑agent baseline. Experiments show that while advanced MLLMs can handle many single‑hop tasks, they struggle with longer trajectories that require coordinating hidden prerequisites, and larger models or different thinking modes do not consistently improve performance.
arXiv Computation and Language
Sep 22
A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents
arXiv:2601.12538v2 Announce Type: replace-cross Abstract: Reasoning is a fundamental cognitive process underlying inference, problem-solving, and decision-making. While large language models (LLMs) d...
arXiv AI
Jun 12
From Digital to Physical: Digital Agents as Autonomous Coaches for Physical Intelligence
arXiv:2601. 21570v2 Announce Type: replace Abstract: The field of Embodied AI is witnessing a rapid evolution toward general-purpose robotic systems, fueled by high-fidelity simulation and large-scale data collection.
arXiv AI
Jun 2
MARFT: Multi-Agent Reinforcement Fine-Tuning
arXiv:2504. 16129v5 Announce Type: replace-cross Abstract: Large Language Model (LLM)-based Multi-Agent Systems (LaMAS) have demonstrated strong capabilities on complex agentic tasks requiring multifaceted reasoning and collaboration, from high-quality presentation generation to scientific research.
arXiv AI
Jun 19
Multi-Agent Transactive Memory
arXiv:2606. 19911v1 Announce Type: new Abstract: The decentralized deployment of LLM agents with diverse capabilities across diverse tasks motivates infrastructure for knowledge sharing across heterogeneous agent populations.
arXiv AI
Aug 12
MEGA: Self-Evolving Agent Optimization Infrastructure via Wisdom Graph
arXiv:2608. 10504v1 Announce Type: new Abstract: As coding agents increasingly handle implementation, the central challenge shifts from building individual agents to building an infrastructure that systematically improves them.