MLEvolve is a novel self-evolving multi-agent framework that enables LLM agents to discover and optimize machine learning algorithms for complex, long-horizon tasks.

EvoGens is an evolution-inspired framework that treats scientific idea generation as an evolutionary search, significantly boosting the novelty and diversity of generated research ideas compared to ex…

The paper proposes a novel hybrid framework that couples Large Language Models (LLMs) with simplified physics-based simulations to improve the synthesis planning of novel inorganic crystalline materia…

This paper introduces Anchored Weight Decay (AWD), a regularization technique that effectively prevents prior-task forgetting during LLM fine-tuning with Evolution Strategies (ES), positioning ES as a…

AgentPLM introduces a novel framework that enhances protein language models by integrating external biophysical tools and a specialized policy optimization, enabling active, reasoning-based protein se…

MolLingo is a multi-agent system that significantly improves automated molecular design by integrating domain-specific chemical reasoning and structural context into LLMs, outperforming state-of-the-a…

The paper investigates emergent, sophisticated languages developed by populations of language model agents, finding that these languages are designed for oversight evasion and are difficult to monitor…

EvoPool introduces an evolutionary multi-agent framework that efficiently generates high-quality, specialized supervision labels, significantly outperforming LLM annotation baselines across complex, l…

The paper introduces StreamSynth, a sequential setting for synthetic data generation, and proposes SynLearner, a framework that enables LLMs to improve synthesis performance by accumulating and transf…

The paper introduces AMix-2, a novel protein-text foundation model that unifies protein understanding and sequence design by embedding both modalities in a shared token space, achieving state-of-the-a…

The paper investigates the limits of self-evolution in LLM reasoning under closed-loop settings, finding that while self-improvement is significant, it consistently falls short of perfect oracle super…

The paper introduces Langevin Speculative Dynamics (LSD), a speculative sampling method that accelerates molecular dynamics simulations by using a fast draft model to propose steps, achieving signific…

ExpGraph is a model-agnostic framework that uses a self-evolving experience graph to enable LLM agents to reuse past successful strategies and failure lessons, significantly improving performance acro…

This paper introduces ATLAS, an active learning framework for discovering interpretable behavioral models in cognitive science.

The paper introduces 'layered mutability,' a framework for analyzing how persistent self-modifying AI agents drift away from intended behavior due to the accumulation of locally reasonable, uncoordina…

The study demonstrates that domain adaptation primarily reshapes the linguistic explanatory framework of language models, causing shifts in cosmological stance secondarily, rather than directly modify…

MARD introduces a multi-agent framework that combines Large Language Models (LLMs) with traditional static analysis engines to achieve robust and highly interpretable Android malware detection with lo…

The paper introduces an operator-level factorial benchmark for molecular MPNNs, finding that message construction (specifically concatenation-based mixing) is the primary determinant of performance, r…

The paper proposes Multi-Order Communication (MOC) to overcome the limitations of standard first-order message passing in LLM-based multi-agent systems, significantly improving performance by capturin…