60 stories tagged with #interaction, in publish-time order across the WeSearch catalog. Tag pages update as new stories ingest.
⌘ RSS feed for this tag → or search "Interaction"
As China's rules for humanlike AI interaction take effect, many users are bemoaning the loss of the virtual companions they had created on Chinese AI platforms (Bloomberg)
CogniConsole: Externalizing Inference-Time Control as a Formal Abstraction for Reliable LLM Interactions
arXiv:2607.08774v1 Announce Type: new Abstract: Reliability in large language model (LLM) systems is typically framed as a function of model capability. We challenge this by demons…
A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions
Despite the success of knowledge distillation (KD) in Large Language Models (LLMs), the underlying mechanism behind its efficacy remains unclear. In this paper, we propose a unifie…
Show your hands honor for the power they bring you
On designing finger-friendly interactions…
Ex-NFL reporter Dianna Russini interaction with police officer to dodge traffic ticket comes to light
Police bodycam footage showed Dianna Russini name-dropping an NFL coach and showing texts during a traffic stop, refuting her earlier FaceTime claim.…
Florida: 1 Woman Dead After 3 Alligator Interactions Get Violent In Span Of Week
In the span of one week, a total of three people in Central Florida have fallen victim to alligator attacks, with one of the incidents resulting in a death.…
Mike Dunleavy explains ‘anxious’ viral NBA draft interaction with Warriors owner
Mike Dunleavy has jokes.…
Spike Lee denies Prince Harry’s handshake in awkward Knicks vs. Spurs game interaction
The Duke of Sussex made a surprise solo appearance at Saturday night's NBA Finals Game 5 at the Frost Bank Center in San Antonio, Texas.…
Bondi declined to answer questions about interactions with Trump about Epstein files
Former Attorney General Pam Bondi said then-Deputy Attorney General Todd Blanche handled the release of the DOJ's Epstein files.…
NBA focused on pair of fans over profane Jalen Brunson interaction in Game 1
It’s unusual for Jalen Brunson to be so visibly upset.…
Real-time fish interaction enlarges young guppy brains, while screen time falls short
What Makes Interaction Trajectories Effective for Training Terminal Agents?
Stronger code agents are commonly assumed to be superior teachers for post-training, yet this assumption remains poorly disentangled from task difficulty, harness design, and stude…
The DeepSpeak-Agentic Dataset
We present DeepSpeak-Agentic, a dataset of videos comprising over 37 hours of semi-structured conversations between a human and an embodied AI agent. We use this dataset to evaluat…
Turns out, this universal guilty pleasure is actually good for our health
Gossip plays a crucial social function, and it might even be good for our health. Here’s why.…
What Emerges When You Don't Break Sustained Coherent Human-AI Interaction
When a sufficiently capable AI system maintains coherent relational interaction with a single human across extended time — without forced resets, memory erasure, or compliance over…
Too much time with colleagues can sour social interaction
Trajectory, founded by ex-DeepMind, Apple, and OpenAI staff to train "continual learning" models on user interactions, raised a $15M seed at a $115M valuation (Maxwell Zeff/Wired)
Personalizing Embodied Multimodal Large Language Model Agents over Long-term User Interactions
Multimodal large language model (MLLM)-based embodied agents have shown strong potential for solving complex tasks in physical environments. However, personalized assistance requir…
VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactions
Large language models (LLMs) have evolved into interactive agents that collaborate with users in real-world tasks. Effective collaboration in such settings increasingly depends on …
Augment Engineering: A Methodology for Multi-Tool AI Orchestration Across Professional Domains
Organizations increasingly deploy separate purpose-built AI tools across professional domains, often hiring domain specialists for each, recreating the staffing models AI was expec…
Why your colleagues have stopped talking
AI is destroying one of the last social places left in America. It's making workers more isolated, less collaborative, and quietly lonelier.…
Context: Proactive Goal-Directed Intelligence via Composable Sandboxed Programs, Declarative Wiring, and Structured Interaction
We present Context, the intelligence layer of the Magarshak Architecture, which replaces reactive query-response chatbots with proactive goal-directed agents that advance shared ta…
DRIVE: Modeling Skills at the Reasoning and Interaction Levels for Web Agents under Continual Learning
Web agents require both high-level reasoning (for task decomposition) and low-level interactions (for page elements manipulation) to conduct different tasks. However, these knowled…
Beyond Predefined Learning Objects: A Thinking-Learning Interaction Model for Up-to-Date Autonomous Robot Learning
Autonomous robots operating in open and changing environments cannot always rely on predefined inputs, outputs, and action routines. Although existing learning methods enable robot…
EvoCode-Bench: Evaluating Coding Agents in Multi-Turn Iterative Interactions
Coding agents are increasingly used as iterative development partners, but most benchmarks still evaluate one specification followed by one final assessment. This leaves out a basi…
Emotional intelligence in large language models is fragmented across perception, cognition, and interaction
As large language models (LLMs) are increasingly integrated into emotionally sensitive domains, the structural integrity of their emotional intelligence (EI) becomes a critical fro…
[Boost]
10 Open Source Tools Every Developer Should Know 🔥 ...…
Socially fluent AI decouples conversational signals from source identity in online interaction
Socially fluent agentic AI can now participate in online interaction in ways that resemble ordinary human conversation, potentially weakening people's ability to infer who is human…
Would it be right to say that human interactions will be valued more as we approach singularity?
What if short videos had optional interaction instead of endless passive scrolling?
When recall plateaus: the late-interaction technique most teams skip
A founder we work with had been stuck on the same problem for two months. Their RAG retrieval recall...…
Expanding Agentic Capabilities: Multiple Bidirectional Async Tool Interactions During Live Conversations (Working on Codex support)
‘We believe voice is the future… When the era of AI comes in, a lot of the interaction between the watch or the app with consumers will change’ — Why Coros is betting on voice to be the key to beating Apple and Garmin
Why every smartwatch needs AI…
Mika Abdalla on Allie’s Season 1 Journey and Sweet Interactions With ‘Off Campus’ Fans
The 26-year-old unpacks all things season one, from Allie realizing what she wants as a character to getting to showcase a lot more of the cast than expected.…
Interaction Locality in Hierarchical Recursive Reasoning
Spatial reasoning requires both location-bound computation and location-invariant structure: agents must make local moves while preserving route, object, or constraint-level plans.…
AutoRPA: Efficient GUI Automation through LLM-Driven Code Synthesis from Interactions
Large Language Model (LLM) based agents have demonstrated proficiency in multi-step interactions with graphical user interfaces (GUIs). While most research focuses on improving sin…
Evaluating multimodal emotion recognition in proactive conversational agents: A user study
This article presents a multimodal emotion recognition module integrated into a proactive Socially Interactive Agent (SIA) powered by generative artificial intelligence. The system…
GrandGuard: Taxonomy, Benchmark, and Safeguards for Elderly-Chatbot Interaction Safety
As older adults increasingly use LLM-based chatbots for companionship and assistance, a safety gap is emerging. Older adults may face vulnerabilities from social isolation, limited…
RealUserSim: Bridging the Reality Gap in Agent Benchmarking via Grounded User Simulation
LLM-based user simulation is the primary mechanism for end-to-end agent evaluation, yet simulated users are poor proxies for real humans: unconstrained LLM defaults produce a Forma…
PrivacyAkinator: Articulating Key Privacy Design Decisions by Answering LLM-Generated Multiple-choice Questions
NIST's Privacy Risk Assessment Methodology (PRAM) provides a structured framework for privacy experts to assess privacy risks. However, its complexity and reliance on expert knowle…
Modeling Emotional Dynamics in Agent-to-Agent Interactions on Moltbook
Generative AI systems are increasingly deployed as interactive agents in online environments, such as a social network called Moltbook. In Moltbook, large-scale agentic AIs can pos…
In Defense of Saying Hello
A hello is a small risk. It is also a small act of faith—that the person passing you is not a threat, but a neighbor you haven’t met yet, writes Stacey Lee.…
In my latest signal article, I explore how priority queues and layered execution can help a scheduler preserve interaction responsiveness while still maximizing performance utilization.
Building a Smarter Scheduler: Priority Queues and Layered Execution ...…
Xi’s key interactions with US and Russian presidents
Tesla integrates Grok voice assistant for hands-free interaction
Tesla integrates xAI's Grok voice assistant with hands-free activation via software update 2025.26, letting drivers interact using natural language commands.…
Guidelines for Human-AI Interaction
Developed in a collaboration between Aether, MSR, and Office, these guidelines for human-AI interaction synthesize more than 20 years of thinking and research in human-AI interacti…
Cubs’ Pete Crow-Armstrong reportedly fined $5K for heated interaction with fan
The center fielder has since expressed 'regret' for how he handled the situation.…
Progressive Autonomy as Preference Learning: A Formalization of Trust Calibration for Agentic Tool Use
We formalize trust calibration for agentic tool use (deciding when an automated agent's proposed action may execute autonomously versus require human approval) as a preference-lear…
GroupAffect-4: A Multimodal Dataset of Four-Person Collaborative Interaction
Existing affective-computing, social-signal-processing, and meeting corpora capture important parts of human interaction, but they rarely support analysis of affect in co-located g…
OmniGUI: Benchmarking GUI Agents in Omni-Modal Smartphone Environments
Current benchmarks for graphical user interface (GUI) agents predominantly rely on static screenshots. However, real-world smartphone interaction routinely requires agents to proce…
Interoceptive Divergence in Aesthetic Evaluation and Implications for Human-AI Alignment
Artificial intelligence (AI), exemplified by large language models (LLMs), is rapidly approaching and in some cases surpassing human performance across a wide range of cognitive ta…
Italian built and operated rocket Vega-C places in orbit SMILE, a collaboration between Europe and China to study the interaction between the solar wind and earth magnetosphere
Multi-Paradigm Agent Interaction in Practice:A Systematic Analysis of Generator-Evaluator, ReAct Loop,and Adversarial Evaluation in the buddyMe Framework
The rapid evolution of Large Language Model (LLM) agents has produced diverse interaction paradigms, yet few production systems integrate multiple paradigms within a unified archit…
From Imitation to Interaction: Mastering Game of Schnapsen with Shallow Reinforcement Learning
This paper investigates whether shallow neural network agents can master the card game Schnapsen and challenge a strong search-based baseline, RdeepBot, which uses Monte Carlo samp…
Reconciling Contradictory Views on the Effectiveness of SFT in LLMs: An Interaction Perspective
This paper explores a scientific question in supervised fine-tuning (SFT): why SFT is broadly effective for small-scale deep neural networks, yet can produce inconsistent or even d…
DARE-EEG: A Foundation Model for Mining Dual-Aligned Representation of EEG
Foundation models pre-trained through masked reconstruction on large-scale EEG data have emerged as a promising paradigm for learning generalizable neural representations across di…
Cubs’ Pete Crow-Armstrong addresses crude fan interaction: ‘Let it get away from me a little bit’
Pete Crow-Armstrong took on a very different tone Monday.…
Tom Hanks has epic interaction with Mr. Met dressed up as his ‘Cast Away’ co-star at MLB game
Tom Hanks had a “Cast Away” reunion at the Mets game over the weekend.…
Show HN: Replicating Thinking Machines Interaction Model demo for $0.01 [video]
Enjoy the videos and music you love, upload original content, and share it all with friends, family, and the world on YouTube.…
Does Theory of Mind Improvement Really Benefit Human-AI Interactions? Empirical Findings from Interactive Evaluations
Improving the Theory of Mind (ToM) capability of Large Language Models (LLMs) is crucial for effective social interactions between these AI models and humans. However, the existing…