Research Feed
Search source-linked summaries of recent AI and machine-learning papers by topic, by date, or by whether they include code or a diagram.
Research results
Magpie is a real-time renderer that uses foundation models to generate game visuals by processing white-box frames as a continuous denoising condition.
The researchers introduced SWE-Prime, a method that selects a small, high-quality subset of training trajectories to improve software engineering agent performance.
The paper introduces a layered composition framework for semantic data processing that integrates online learning components to reduce the cost of LLM-based query execution.
WikiSkill improves AI agent performance by consolidating execution traces into a structured, persistent wiki that informs future skill development.
CritICL improves large language model performance by providing targeted, failure-aware critique examples in the prompt to steer reasoning away from common pitfalls.
The PILOT harness allows AI agents to improve their performance in real time by employing a supervisor that provides live feedback and distills successful strategies during task execution.
The paper introduces UrbanGround, a sandbox environment using real-world 3D mapping data to evaluate how well MLLM agents navigate complex urban settings.
The ACE framework establishes a formal structure for evaluating and improving the data generated to train autonomous AI agents.
The paper introduces PAWBench, a new evaluation framework that measures how well video generation models predict the physical outcomes of various scenarios.
TTPO improves the reasoning accuracy of language models during test time by using label-free policy optimization that bypasses the need for manual ground-truth data.
The paper introduces Agent Mesh to address unique reliability challenges in agentic software development by defining new primitives to manage non-idempotent tool delegations.
The paper introduces a dual-domain architectural pattern that separates an AI agent's persona from its execution logic to improve governance and auditability in regulated environments.
The authors introduce SymTrace, a framework that improves the reliability of debugging complex multi-agent systems by using controlled intervention anchors to replicate and repair execution failures.
TAU-Agent is an agentic framework designed to improve traffic anomaly detection by using retrieval-augmented generation to integrate video descriptions and object trajectories.
PlanSightRAG leverages a vision-first multimodal framework to automate compliance checking for complex civil engineering drawings.
The authors introduce a framework for video-editing agents to generate and verify executable edit plans using a self-improving training loop.
The research demonstrates that providing prior evaluation scores as metadata to LLM-as-a-judge systems causes systematic anchoring bias that distorts final judgment accuracy.
The researchers introduced XRepoTest to evaluate how effectively large language models generate unit tests within complex, multi-file code repositories across five programming languages.
The researchers developed a vision-language-action model designed to improve how multiple robotic arms collaborate on complex tasks by using techniques that enforce role-agnostic instruction following.
The paper introduces a method that uses vision-language models to perform reasoning that guides robot manipulation policies, improving performance on long-horizon tasks.