All Articles
17653 articles total
EvoMaster: A Foundational Evolving Agent Framework for Agentic Science at Scale
EvoMaster is a self-evolving agent framework for scientific discovery that enables agents to iteratively refine hypotheses and accumulate knowledge.
LiteResearcher: A Scalable Agentic RL Training Framework for Deep Research Agent
LiteResearcher is a scalable RL training framework that uses a virtual world to train deep research agents more efficiently and effectively.
Are Performance-Optimization Benchmarks Reliably Measuring Coding Agents?
An audit of performance-optimization benchmarks for coding agents (GSO, SWE-Perf, SWE-fficiency) reveals significant instabilities and scoring flaws that may misrepresent agent progress.
FurnitureVLA: Learning Long-Horizon Bimanual Furniture Assembly with Vision-Language-Action Model
Researchers introduce FurnitureVLA, a Vision-Language-Action model designed for long-horizon bimanual furniture assembly using a progress-enhanced VLA and VR teleoperation for data collection.
The State-Prediction Separation Hypothesis
The state-prediction separation hypothesis proposes a Transformer variant that disentangles token prediction from state storage, leading to better data and compute efficiency.
Language-Critique Imitation Learning from Suboptimal Demonstrations
A new language-critique framework for imitation learning uses structured natural language feedback instead of scalar signals to learn robust policies from suboptimal demonstrations.
Measuring the Gap Between Human and LLM Research Ideas
A study on research ideation finds that LLM-generated ideas are more narrow and systematically different from human-generated ideas, often focusing on synthesis rather than diverse framing.
Unexplainability of Artificial Intelligence Judgments and Functional Implementation in Kant's Perspective
This paper applies Kant's theory of judgment to AI, arguing that the Softmax function reframes AI judgments as mere possibility judgments, making true functional implementation unexplainable.
From Silos to Systems: Process-Oriented Hazard Analysis for AI Systems
The authors present PHASE, a guideline for process-oriented hazard analysis for AI systems based on the System Theoretic Process Analysis (STPA) framework to identify system-level risks.
Selective Expert Guidance for Effective and Diverse Exploration in Reinforcement Learning of LLMs
MENTOR is introduced as a framework for Reinforcement Learning with Verifiable Rewards (RLVR) that provides expert guidance only at critical decision points to improve exploration diversity.
Large language models replicate and predict human cooperation across experiments in game theory
Research shows that specific LLMs, particularly Llama, can replicate human cooperation patterns in game-theoretic experiments with high fidelity, suggesting a mechanistic basis for human-like behavior.
CoT-X: An Adaptive Framework for Cross-Model Chain-of-Thought Transfer and Optimization
CoT-X is an adaptive framework that compresses Chain-of-Thought reasoning traces via semantic segmentation, reducing inference overhead while maintaining accuracy across different LLM scales.
Muon as a Residual Connection
Proposes a mechanistic interpretation of the Muon optimizer as an implicit residual connection that balances local gradient descent with representation preservation.
Autonomous Scientific Discovery via Iterative Meta-Reflection
Introduces DiscoPER, an LLM-powered framework for autonomous scientific discovery that uses iterative meta-reflection and code execution to explore datasets.
Skills Are Not Islands: Measuring Dependency and Risk in Agent Skill Supply Chains
Introduces Agent Skill Supply Chains (ASSCs) and the SkillDepAnalyzer tool to manage and audit dependencies in LLM agent skills, improving security and provenance.
Sequentially-Controlled Interactive Multi-Particle Flow-Maps for Online Feedback-Driven Search
Presents IMPFM, a framework for sample-efficient online feedback-driven search using multi-particle flow-maps to prevent mode collapse and reward over-optimization.
Adversarial Pragmatics for AI Safety Evaluation: A Benchmark for Instruction Conflict, Embedded Commands, and Policy Ambiguity
Introduces a benchmark for adversarial pragmatics to evaluate LLM behavior under instruction conflict, policy ambiguity, and embedded commands for better AI safety audits.
Diffusion-GR2: Diffusion Generative Reasoning Re-ranker
Introduces Diffusion-GR2, which converts autoregressive reasoning re-rankers into block-diffusion models to significantly increase throughput while maintaining accuracy.
Right in the Right Way: LM Training with Verifiable Rewards and Human Demonstrations
Proposes an adversarial generator-discriminator framework to combine verifiable rewards with human demonstrations, reducing reward hacking and improving output style in RL training.
World from Motion: Generative Dynamic Gaussian Reconstruction from Monocular Video
Presents 'World from Motion', a method for generating high-quality dynamic 3D Gaussian representations from monocular videos by distilling video model generations.