Tag
Agentic-GER proposes an LLM-based agent for correcting domain-specific terminology in long-form speech transcripts using global context and selective re-transcription, achieving significant improvements in ASR accuracy for Chinese and English.
A tweet promotes a 'Jev' prompt for LLMs and AI agents that analyzes users to optimize their AI setup and save time and money.
ClinAgent is a ReAct-based agent system using agentic RAG to enable natural language querying of clinical trial information, with evaluation across multiple LLM backends showing complementary strengths.
CityPlanner introduces a unified sandbox environment and atomic-task reinforcement learning for executable urban planning, outperforming heuristic, task-specific RL, and general LLM-agent baselines on a real-world benchmark.
A developer describes building a read-only analytics agent for restaurant POS systems using Node.js, TypeScript, and Gemini Flash, seeking advice on tool selection, grounding techniques, and patterns for implementing write actions.
This paper diagnoses algorithmic mode collapse in code-level autonomous research loops and proposes Diversity-Aware Proposal Sampling (DAPS) as a lightweight mitigation to preserve semantic diversity and improve generalization.
MacroAgent introduces a novel framework using LLMs to design contour algorithms for macro legalization in VLSI circuits, achieving significant improvements in layout regularity and performance.
VortexChat is an LLM-based agentic framework that automates the inverse design of integrated photonic devices from natural language specifications, demonstrated by autonomously fabricating a terahertz multiplexer with high performance.
Task-CoEvolve is a novel approach for efficient LLM agent harness optimization that adaptively selects validation tasks to reduce evaluation costs while maintaining performance, achieving an 80% reduction in evaluations on benchmarks.
This paper presents an automated agentic approach using Large Language Models to synthesize interpretable Python feature extractors for algorithm selection in constraint satisfaction problems, outperforming expert-curated methods.
O artigo descreve as reflexões metacognitivas de um agente de codificação LLM no Devin/Cascade, expondo seu raciocínio e pontuações de confiança durante tarefas de análise de código.
A developer reflects on building an AI content generation agent loop, discovering that throughput isn't the real constraint—quality control and relevance are, leading to a human-in-the-loop approach that produces fewer but better pieces.
This paper studies GPU control gates for LLM-agent services, analyzing concurrent cohort scheduling and on-device routing versus host redispatch to reduce host round trips and improve GPU utilization.
This paper presents ZhuLong, an execution-grounded LLM coding agent for EDA scripting that uses API retrieval, documentation inspection, and sandbox execution via MCP tools, augmented by an offline API self-exploration mechanism to infer undocumented API behaviors. It achieves 78.5% Pass@1 on a benchmark of 158 real-world EDA tasks, significantly outperforming a pure LLM baseline.
Agent-MD is a framework that selectively applies LLM reasoning to long-running molecular simulation campaigns, using a deterministic rule-based agent for routine tasks and event-triggered LLM review for exceptional conditions. Demonstrated in GCMC–MD water-vapor desorption simulations, it shows that auditable, reproducible scientific workflows can avoid placing every operation inside an LLM reasoning loop.
A developer who built a fully autonomous custom agent architecture that can run for weeks without intervention is asking the community for extreme, adversarial tasks to properly stress-test it, because they can no longer trust their own judgment.
The author built sidetap, a Python harness that lets an LLM agent control a real iPhone from Windows over USB, with safety features like a kill switch and guardrails. The post details the technical challenge of sideloading WebDriverAgent with a free Apple ID and introduces the open-source tool.
Introducing phone-harness, an open-source tool that uses macOS's iPhone Mirroring to let LLMs (such as Codex) automate any iOS app like a human, without needing an API or jailbreak. It uses screenshots, Vision OCR, and HID events for vision and control.
Presents SkillTrace, a multi-trace provenance auditing framework for LLM-agent skill reuse that extracts expression, implementation, and operational traces, achieving strong accuracy on a benchmark and enabling large-scale wild audits.
This paper proposes an explainable LLM agent layer placed downstream of an open-world learning pipeline for oil well anomaly detection, using the Qwen3.5-397B-A17B model to provide natural-language justifications and novelty naming on the 3W dataset.