arXiv AI
View-oriented Conversation Compiler for Agent Trace Analysis
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computation and Language
Nov 2
SimXAI: A Simple Drop-in Layer Increases Interaction Quality and Understanding in Conversational XAI
SimXAI is a lightweight, LLM‑centric conversational layer that replaces traditional intent recognition, dialogue management, and template‑based response modules in GUS‑style ConvXAI agents. By using a single tool‑calling LLM to interface with existing XAI resources, it provides a modular interface that improves function‑selection accuracy, faithfulness, and handling of context‑dependent requests. In a user study, substituting SimXAI for the conversational layer of the TalkToModel agent led to more accurate task completion in fewer turns, demonstrating enhanced conversational quality while preserving faithfulness.
arXiv AI
3d ago
The Power of Meta Access in the Software of the Future --- Demonstrated on LLM Chat UIs and Chat AI
The paper proposes ‘meta access’—a structured, permissioned view of an interface’s state—to enhance large language model chat UIs. It outlines a ladder of access levels, from feature tutoring to full orchestration, and demonstrates the concept with the Meta Chat prototype, which uses summaries, settings, and message links to enable reversible changes and a browsable tutorial library. Meta access aims to transform chat from a single conversation window into a control layer for the entire workspace while addressing risks such as grounding, privacy, and prompt injection.
arXiv Computation and Language
Oct 15
ContextWeaver: Selective and Dependency-Structured Memory Construction for LLM Agents
arXiv:2604.23069v2 Announce Type: replace Abstract: Large language model (LLM) agents often struggle in long-context interactions. As the history grows, sliding windows and prompt compression may dro...
arXiv Computation and Language
Aug 28
Agent Seer: Synthesizing Scenarios from Specification Understanding
Agent Seer is a pipeline that automatically synthesizes realistic evaluation scenarios for AI agents that use external tools, using only the tool’s specification (function names, natural‑language descriptions, and typed parameter schemas). Starting from a single Model Context Protocol (MCP) specification, it enriches raw schemas, generates graded scenarios with synthetic tool outputs, and expands them into mock‑data‑grounded multi‑turn dialogues that demonstrate strong tool‑calling correctness and conversational coherence. Across seven diverse MCP specifications, the pipeline achieves high quality, with parameter‑schema complexity emerging as the main driver of quality variation and argument‑value accuracy identified as the dominant failure mode.
arXiv AI
Oct 15
A Decade in a Day: Synthesizing Agent-Native Interfaces from Human-Oriented Software Evolution
arXiv:2610.15765v1 Announce Type: cross Abstract: Large language model agents are emerging as an important new class of users of desktop applications. However, existing desktop interfaces were design...
arXiv AI
Jun 9
WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces
arXiv:2606. 09426v1 Announce Type: new Abstract: Computer-use agents (CUAs) increasingly operate in runtimes that combine visual desktop control, command-line execution, code editing, browsers, and external tools.