Tootfinder

Day 26: Emily Short
If you know who Short is, you know exactly why she's on this list. If you don't, you're probably in the majority. She's an absolutely legendary author within the interactive fiction (IF) community, which gets somewhat pigeonholed by stuff like Zork when there's actually a huge range of stuff in the medium some of which isn't even puzzle-focused, and Short has been writing & coding on the bleeding edge of things for decades.
I was lucky enough to be introduced to Short's work in graduate school, where we played "Galatea" as part of an interactive fiction class. Short uses a lot of clever parser tricks to make your conversation with a statue feel very fluid and conversational, giving to contemporary audiences a great example of how vibrant interaction with a well-designed agent can be in contrast to an LLM, if you're willing to put in some work on bespoke parsing & responses (although the user does need to know basic IF conventions). While I didn't explore the full range of Galatea's many possible outcomes, it left a strong impression on me as a vision for what IF could be besides dorky puzzles, and I think that "visionary" is a great term to describe Short.
If you'd like you get a feel for her (very early) work, you can play Galatea here: #30AuthorsNoMen

Introducing "Hey #Copilot..." that recognizes what's happening on the screen to understand what you're doing.
Now with a built-in voice agent that does GENERAL #AUTOMATION for user tasks.
✅ Making every

GOAT: A Training Framework for Goal-Oriented Agent with Tools
Hyunji Min, Sangwon Jung, Junyoung Sung, Dosung Lee, Leekyeung Han, Paul Hongsuck Seo
https://arxiv.org/abs/2510.12218

GOAT: A Training Framework for Goal-Oriented Agent with Tools
Large language models (LLMs) have recently been extended beyond traditional text generation to serve as interactive agents capable of using external tools based on user intent. However, current LLM agents still show limited ability to handle goal-oriented queries, which require decomposing a high-level objective into multiple interdependent API calls with correct planning and execution. Current approaches mainly rely on zero-shot evaluation due to the absence of training data. While proprietary…

RA-Gen: A Controllable Code Generation Framework Using ReAct for Multi-Agent Task Execution
Aofan Liu, Haoxuan Li, Bin Wang, Ao Yang, Hui Li
https://arxiv.org/abs/2510.08665 htt…

RA-Gen: A Controllable Code Generation Framework Using ReAct for Multi-Agent Task Execution
Code generation models based on large language models (LLMs) have gained wide adoption, but challenges remain in ensuring safety, accuracy, and controllability, especially for complex tasks. Existing methods often lack dynamic integration of external tools, transparent reasoning, and user control over safety. To address these issues, we propose a controllable code generation framework utilizing the ReAct paradigm for multi-agent task execution. This framework is a multi-agent system designed to…

@… I’m playing catch-up on your weekly updates (you no longer shows in my feed or alerts even though I follow you, which is hella annoying and I still have to debug) and think you were messing with me by generating the abstract of my Atlass post with an LLM.
If so, well done and I’m sorry I’m just seeing it.
If not, then I guess I need bet…

AgentBuilder: Exploring Scaffolds for Prototyping User Experiences of Interface Agents
Jenny T. Liang, Titus Barik, Jeffrey Nichols, Eldon Schoop, Ruijia Cheng
https://arxiv.org/abs/2510.04452

AgentBuilder: Exploring Scaffolds for Prototyping User Experiences of Interface Agents
Interface agents powered by generative AI models (referred to as "agents") can automate actions based on user commands. An important aspect of developing agents is their user experience (i.e., agent experience). There is a growing need to provide scaffolds for a broader set of individuals beyond AI engineers to prototype agent experiences, since they can contribute valuable perspectives to designing agent experiences. In this work, we explore the affordances agent prototyping systems should off…

ReInAgent: A Context-Aware GUI Agent Enabling Human-in-the-Loop Mobile Task Navigation
Haitao Jia, Ming He, Zimo Yin, Likang Wu, Jianping Fan, Jitao Sang
https://arxiv.org/abs/2510.07988

ReInAgent: A Context-Aware GUI Agent Enabling Human-in-the-Loop Mobile Task Navigation
Mobile GUI agents exhibit substantial potential to facilitate and automate the execution of user tasks on mobile phones. However, exist mobile GUI agents predominantly privilege autonomous operation and neglect the necessity of active user engagement during task execution. This omission undermines their adaptability to information dilemmas including ambiguous, dynamically evolving, and conflicting task scenarios, leading to execution outcomes that deviate from genuine user requirements and pref…

WebGen-Agent: Enhancing Interactive Website Generation with Multi-Level Feedback and Step-Level Reinforcement Learning
Zimu Lu, Houxing Ren, Yunqiao Yang, Ke Wang, Zhuofan Zong, Junting Pan, Mingjie Zhan, Hongsheng Li
https://arxiv.org/abs/2509.22644

WebGen-Agent: Enhancing Interactive Website Generation with Multi-Level Feedback and Step-Level Reinforcement Learning
Agent systems powered by large language models (LLMs) have demonstrated impressive performance on repository-level code-generation tasks. However, for tasks such as website codebase generation, which depend heavily on visual effects and user-interaction feedback, current code agents rely only on simple code execution for feedback and verification. This approach fails to capture the actual quality of the generated code. In this paper, we propose WebGen-Agent, a novel website-generation agent tha…

facebookexternalhit/1.1 Facebot Twitterbot/1.0
If you see that in a user agent string in your web logs, someone at or behind the source address has probably shared the URL in an Apple iMessage as a result of the link preview function.
Enabling Lockdown Mode on the iPhone should prevent that that preview fetch.

Cooperative Flexibility Exchange: Fair and Comfort-Aware Decentralized Resource Allocation
Rabiya Khalid, Evangelos Pournaras
https://arxiv.org/abs/2510.04192 https://

Cooperative Flexibility Exchange: Fair and Comfort-Aware Decentralized Resource Allocation
The growing electricity demand and increased use of smart appliances are placing new pressures on power grids, making efficient energy management more important than ever. The existing energy management systems often prioritize system efficiency (balanced energy demand and supply) at the expense of user comfort. This paper addresses this gap by proposing a novel decentralized multi-agent coordination-based demand-side management system. The proposed system enables individual agents to coordinat…

BrowserArena: Evaluating LLM Agents on Real-World Web Navigation Tasks
Sagnik Anupam, Davis Brown, Shuo Li, Eric Wong, Hamed Hassani, Osbert Bastani
https://arxiv.org/abs/2510.02418

BrowserArena: Evaluating LLM Agents on Real-World Web Navigation Tasks
LLM web agents now browse and take actions on the open web, yet current agent evaluations are constrained to sandboxed environments or artificial tasks. We introduce BrowserArena, a live open-web agent evaluation platform that collects user-submitted tasks, runs Arena-style head-to-head comparisons, and uses step-level human feedback to surface failure modes. Collecting and analyzing step-level annotations on the agent traces, we identify three consistent failure modes: captcha resolution, pop-…

Prototyping Multimodal GenAI Real-Time Agents with Counterfactual Replays and Hybrid Wizard-of-Oz
Frederic Gmeiner, Kenneth Holstein, Nikolas Martelaro
https://arxiv.org/abs/2510.06872

Prototyping Multimodal GenAI Real-Time Agents with Counterfactual Replays and Hybrid Wizard-of-Oz
Recent advancements in multimodal generative AI (GenAI) enable the creation of personal context-aware real-time agents that, for example, can augment user workflows by following their on-screen activities and providing contextual assistance. However, prototyping such experiences is challenging, especially when supporting people with domain-specific tasks using real-time inputs such as speech and screen recordings. While prototyping an LLM-based proactive support agent system, we found that exis…

Mano Report
Tianyu Fu, Anyang Su, Chenxu Zhao, Hanning Wang, Minghui Wu, Zhe Yu, Fei Hu, Mingjia Shi, Wei Dong, Jiayao Wang, Yuyang Chen, Ruiyang Yu, Siran Peng, Menglin Li, Nan Huang, Haitian Wei, Jiawei Yu, Yi Xin, Xilin Zhao, Kai Gu, Ping Jiang, Sifan Zhou, Shuo Wang
https://arxiv.org/abs/2509.17336…

Mano Report
Graphical user interfaces (GUIs) are the primary medium for human-computer interaction, yet automating GUI interactions remains challenging due to the complexity of visual elements, dynamic environments, and the need for multi-step reasoning. Existing methods based on vision-language models (VLMs) often suffer from limited resolution, domain mismatch, and insufficient sequential decisionmaking capability. To address these issues, we propose Mano, a robust GUI agent built upon a multi-modal foun…