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.

Filter papers All papers

Browse by date

Resource filters

Sort options

Research results

Efficiency & Inference / Multimodal By Xiaoyu Zhan 2026-08-27 7
Magpie: Real-Time World Renderer for Interactive Games

Magpie is a real-time renderer that uses foundation models to generate game visuals by processing white-box frames as a continuous denoising condition.

Agents / Training & Fine-Tuning By Dewu Zheng 2026-08-27
SWE-Prime: Fewer Trajectories, Better Performance

The researchers introduced SWE-Prime, a method that selects a small, high-quality subset of training trajectories to improve software engineering agent performance.

Efficiency & Inference By Paweł Liskowski 2026-08-27
Compositional Online Learning for Semantic Data Processing Systems

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.

Agents / Benchmarks & Evals By Liyan Tang 2026-08-27
WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution

WikiSkill improves AI agent performance by consolidating execution traces into a structured, persistent wiki that informs future skill development.

Reasoning / Efficiency & Inference By Yufan Wu 2026-08-27
CritICL: Inference-Time Weak-to-Strong Generalization from Small Language Model Failure Modes

CritICL improves large language model performance by providing targeted, failure-aware critique examples in the prompt to steer reasoning away from common pitfalls.

Agents / Efficiency & Inference By Yang Xiao 2026-08-27 25
PILOT in the Loop: Live Self-Improvement for Long-Horizon Agents

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.

Agents / Benchmarks & Evals By Tianjie Ju 2026-08-27
UrbanGround: From Local Perception to Spatial Agency in a Real-Scale City

The paper introduces UrbanGround, a sandbox environment using real-world 3D mapping data to evaluate how well MLLM agents navigate complex urban settings.

Agents / Benchmarks & Evals By Xingshan Zeng 2026-08-27
What Makes Good Agentic Data? An ACE Lens on Data Generation for LLM Agents

The ACE framework establishes a formal structure for evaluating and improving the data generated to train autonomous AI agents.

Multimodal / Benchmarks & Evals By Yuandong Pu 2026-08-27
PAWBench: How Far Are We from Probabilistically Aligned World Modeling?

The paper introduces PAWBench, a new evaluation framework that measures how well video generation models predict the physical outcomes of various scenarios.

Reasoning / Reinforcement Learning By Aozhe Wang 2026-08-27
TTPO: Test-Time Policy Optimization

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.

Agents / Efficiency & Inference By Mazhar Shaikh 2026-08-26
Agent Mesh: Reliability Primitives for Non-Idempotent Agent Delegation - Identity Adequacy and Evidence Adequacy

The paper introduces Agent Mesh to address unique reliability challenges in agentic software development by defining new primitives to manage non-idempotent tool delegations.

Agents / Safety & Alignment By Yisen Xi 2026-08-27
Persona-Execution Separation: An Architecture Pattern for Evolving LLM Agents under Execution Audit

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.

Agents / Benchmarks & Evals By Zhongwen Luan 2026-08-26
Repair or Resample? Rethinking Failure Debugging in LLM Multi-Agent Systems

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.

Agents / Multimodal By Yuqiang Lin 2026-08-26
TAU-Agent: An Agentic Retrieval-Augmented Framework for Traffic Anomaly Understanding

TAU-Agent is an agentic framework designed to improve traffic anomaly detection by using retrieval-augmented generation to integrate video descriptions and object trajectories.

Multimodal / Benchmarks & Evals By Nabaraj Subedi 2026-08-26
PlanSightRAG: A Visual-First Multimodal RAG for Automating Question Answering and Compliance Checking for Civil Standard Plans

PlanSightRAG leverages a vision-first multimodal framework to automate compliance checking for complex civil engineering drawings.

Agents / Benchmarks & Evals By Haoyu Wang 2026-08-26
Plans You Can Check: Verifier-Grounded Learning of an Open-Weight Planner for Executable Video-Editing

The authors introduce a framework for video-editing agents to generate and verify executable edit plans using a self-improving training loop.

Benchmarks & Evals By Ante Kapetanovic 2026-08-26
Anchoring Bias in LLM-as-a-Judge Systems: Prior Scores Compromise Evaluation Independence

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.

Benchmarks & Evals By Dung Le Quang 2026-08-26
XREPOTEST: Benchmarking Multilingual Repository-Level Unit Test Generation for Large Language Models

The researchers introduced XRepoTest to evaluate how effectively large language models generate unit tests within complex, multi-file code repositories across five programming languages.

Robotics / Multimodal By Zaibin Zhang 2026-08-26
MA-VLA: Multi-Arm Vision-Language-Action Model for Collaboration and Compositional Generalization

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.

Robotics / Reinforcement Learning By Lehong Wu 2026-08-26
$R^3$: Training Robots to Reason in Natural Language via Reinforcement Learning

The paper introduces a method that uses vision-language models to perform reasoning that guides robot manipulation policies, improving performance on long-horizon tasks.