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…

EvoMD-LLM introduces a novel framework that models reactive molecular dynamics as a symbolic temporal language problem, enabling LLMs to accurately predict complex, time-evolving chemical processes.

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…

SCOPE introduces a data-free self-play framework that co-evolves a task-generating Challenger and a document-answering Solver, significantly improving open-ended performance on language models without…

The paper introduces LearnWeak, an annotation-free framework that automatically specializes small computer-use agents by identifying and targeting their specific weaknesses using a stronger reference…

BenchEvolver introduces a solution-centric evolutionary framework to automatically transform saturated coding benchmarks into significantly harder, high-quality, and diverse evaluation suites.

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…

The paper introduces SkillBrew, a multi-objective framework that treats skill bank curation as a constrained optimization problem to build efficient and well-curated skill repositories for LLM agents.

MOOSE-Copilot is a novel web-based framework that unifies scientific hypothesis discovery by formalizing human-AI interaction, significantly improving performance over autonomous LLM baselines.

The paper introduces RAG-Pref, a novel, training-free Retrieval Augmented Generation (RAG) method for preference alignment that significantly improves LLM refusal guardrails against agentic attacks wi…

The paper introduces TASTE, an automatic task synthesis method that generates challenging agent benchmarks by evolving tool sequences, demonstrating that existing benchmarks are saturated and that TAS…

ExpWeaver introduces a novel framework for LLM agents to learn from past experiences using latent retrieval-augmented generation, achieving state-of-the-art performance while significantly improving t…

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…

The paper introduces Unified Context Evolution (UCE), a gradient-free framework that externalizes and manages agent experience into a typed, evolving library, significantly improving performance on mu…

Mellum 2 is an open-weight 12B Mixture-of-Experts (MoE) language model specialized for software engineering, achieving performance competitive with larger models while maintaining the efficiency of a…

The paper introduces SAVE, a framework that uses on-policy feedback and the value function to self-supervise and improve reward models, significantly enhancing RLHF performance across multiple benchma…

The paper introduces PithTrain, a compact, agent-native Mixture-of-Experts (MoE) training framework that significantly improves agent-task efficiency compared to existing production stacks.

Frontier LLM-based agents can effectively overcome the manual bottleneck of phenotype annotation by achieving consistency comparable to human experts, significantly outperforming existing NLP tools.

EchoRL proposes a lightweight module to exploit valuable learning signals from advantage-degenerated rollouts in Reinforcement Learning with Verifiable Rewards (RLVR), significantly improving LLM post…