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

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.

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.

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.

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.

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.

Agents By Yifan Shi 2026-08-26 6
A Programming Paradigm for Spatiotemporal Composability

The authors introduce a framework called Cordis that uses a context paradigm to enable reliable dynamic composition of software components.

Agents / Multimodal By Yiwen Chen 2026-08-26
Code World Model: Coding Agent as World Brain

The paper introduces a framework where a coding agent generates deterministic code to manage world state, which then guides a video model to maintain visual consistency in simulated environments.

Agents / Benchmarks & Evals By Tianyi Xiong 2026-08-25 11
Rubrics as Visual-Repair Context for Self-Evolving UI-to-Code Generation

RubSE improves AI code generation for web pages by using structured visual rubrics to guide iterative, self-evolving refinements.

Agents / Benchmarks & Evals By Guo Gan 2026-08-25 12
Are Android GUI Agents Robust Against Runtime Anomalies? AnTrap: Evaluating Agents in Dynamic Adversarial Environments

The paper introduces AnTrap, a benchmark that tests how Android GUI agents handle dynamic environmental anomalies by injecting perturbations into 236 tasks.

Agents / Benchmarks & Evals By Liangcai Su 2026-08-25 91
FrontierChallenge: Evaluating Scientific Workflow Completion

The paper introduces FrontierChallenge, a benchmark for evaluating how well AI agents complete end-to-end scientific workflows.

Agents / Efficiency & Inference By Zhifei Xie 2026-08-26
VoiceMem: Streaming Dual-Brain Memory for Real-Time Interaction

VoiceMem is a dual-brain architecture designed to provide accurate, low-latency memory retrieval for speech-based conversational agents.

Agents / Multimodal By Min Zeng 2026-08-26
VISA: Agentic Self-Evolving Data Synthesis for Multimodal Instruction Following

The researchers developed an agentic, iterative framework called VISA to generate high-quality training data for multimodal models by using feedback-driven loops instead of static one-pass pipelines.

Agents / Benchmarks & Evals By Jiarui Yan 2026-08-26
TraceML: An Empirical Analysis of Human-Agent Planning in Machine Learning Development

The paper introduces a planning framework for AI coding agents that aligns their development processes with human practices to improve task performance.

Agents / Efficiency & Inference By Guibin Zhang 2026-08-26 25
JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolution

JIT-Agent improves agent performance by dynamically generating and evolving task-specific control structures just in time to meet individual task demands.

Agents / Benchmarks & Evals By Srimonti Dutta 2026-08-26
Trace Integrity for LLM Data Agents: A Vision for Auditable Structured Reasoning in Real-World Systems

The paper introduces trace integrity metrics to detect silent failures where LLM data agents produce correct answers through invalid logical steps.