Related papers: ContextEcho: A Benchmark for Persona Drift in Long…
Large Language Models (LLMs) increasingly use persistent memory from past interactions to enhance personalization and task performance. However, this memory introduces critical risks when sensitive information is revealed in inappropriate…
We introduce CONCORD, a privacy-aware asynchronous assistant-to-assistant (A2A) framework that leverages collaboration between proactive speech-based AI. As agents evolve from reactive to always-listening assistants, they face a core…
Large language models require consistent behavioral patterns for safe deployment, yet there are indications of large variability that may lead to an instable expression of personality traits in these models. We present PERSIST (PERsonality…
Real-time voice assistants must revise task state when users interrupt mid-response, but existing spoken-dialog benchmarks largely evaluate turn-based interaction and miss this failure mode. We introduce EchoChain, a controlled benchmark…
AI agents are increasingly embedded in real software systems, where they execute multi-step workflows through multi-turn dialogue, tool invocations, and intermediate decisions. These long execution histories, called agentic traces, make…
We introduce Self-Anchoring Calibration Drift (SACD), a hypothesized tendency for large language models (LLMs) to show systematic changes in expressed confidence when building iteratively on their own prior outputs across multi-turn…
Next-generation AI must manage vast personal data, diverse tools, and multi-step reasoning, yet most benchmarks remain context-free and single-turn. We present ASTRA-bench (Assistant Skills in Tool-use, Reasoning \& Action-planning), a…
Today's AI assistants such as OpenClaw are designed to handle context effectively, making context learning an increasingly important capability for models. As these systems move beyond professional settings into everyday life, the nature of…
LLM assistant personalities play a critical role in user experience and perceived response quality. We present a large-scale experiment of frontier LLM personalities using external ELO-based traits scoring across 144 traits. We find that…
As Large Language Models shift the programming toward human-guided ''vibe coding'', agentic coding tools increasingly rely on models to self-diagnose and repair their own subtle faults -- a capability central to autonomous software…
As terminal agents scale to long-horizon, multi-turn workflows, a key bottleneck is not merely limited context length, but the accumulation of noisy terminal observations in the interaction history. Retaining raw observations preserves…
Large language models are increasingly deployed in multi-turn settings such as tutoring, support, and counseling, where reliability depends on preserving consistent roles, personas, and goals across long horizons. This requirement becomes…
Current dialogue systems are not very engaging for users, especially when trained end-to-end without relying on proactive reengaging scripted strategies. Zhang et al. (2018) showed that the engagement level of end-to-end dialogue models…
Copresence verification based on context can improve usability and strengthen security of many authentication and access control systems. By sensing and comparing their surroundings, two or more devices can tell whether they are copresent…
During complex knowledge work, people engage in iterative sensemaking: interpreting information, connecting ideas, and refining their understanding. Yet in current human-AI collaboration, these cognitive processes are difficult to share and…
Long-term interaction with LLM-based systems may produce alignment drift: a gradual process in which system outputs become less constrained by the user's current message and more shaped by prior interaction history, while still appearing…
We introduce SWE-PRBench, a benchmark of 350 pull requests with human-annotated ground truth for evaluating AI code review quality. Evaluated against an LLM-as-judge framework validated at kappa=0.75, 8 frontier models detect only 15-31% of…
In human conversation, empathic dialogue requires nuanced temporal cues indicating whether the conversational partner is paying attention. This type of "active listening" is overlooked in the design of Conversational Agents (CAs), which use…
Modeling discourse -- the linguistic phenomena that go beyond individual sentences, is a fundamental yet challenging aspect of natural language processing (NLP). However, existing evaluation benchmarks primarily focus on the evaluation of…
As spoken dialogue systems expand beyond traditional assistant roles to encompass diverse personas -- such as authoritative instructors, uncooperative merchants, or distracted workers -- they require distinct, human-like turn-taking…