arXiv AI
Jul 21
Interactive Task Alignment as a POMDP
arXiv:2607. 16412v1 Announce Type: new Abstract: Current benchmarks for language models primarily evaluate execution on fully specified tasks.
Beyond Oracle Communication: Benchmarking Interactive Intent Alignment Under Miscommunication and Evolving User Intent
Related stories
arXiv Machine Learning
Jul 24
LLMs Get Lost in Evolving User Intent
arXiv:2607. 20734v1 Announce Type: new Abstract: As LLMs become more capable, they are increasingly deployed as collaborative agents, taking on user-delegated tasks through iterative interaction.
arXiv AI
Sep 1
Evaluating LLMs on Conversational Text-to-SQL under Chain Ambiguity and Intent Drift
arXiv:2608.29543v1 Announce Type: cross Abstract: Recent advances in large language models (LLMs) have established conversational text-to-SQL as a practical interface between users and databases, oft...
arXiv AI
Jul 3
SkillFuzz: Fuzzing Skill Composition for Implicit Intents Discovery in Open Skill Marketplaces
arXiv:2607. 02345v1 Announce Type: cross Abstract: Large Language Model (LLM)-based agents increasingly automate software engineering tasks through reusable skills, natural-language instruction documents that guide planning and execution.
arXiv Computation and Language
Aug 28
INTENT-AS-A-TOOL Makes it Easy to Track Agentic Misalignment
The paper introduces INTENT-AS-A-TOOL, a method that equips large language models with intent-targeted tools to provide a fine-grained, judge‑free signal of their commitment to specific behaviors during reasoning. By monitoring the probability of calling these intent tools, the authors can track how intent evolves throughout generation, complementing chain‑of‑thought monitoring and expanding post‑hoc labels into dense trajectories. The approach identifies critical steps for online intervention, demonstrating that action preferences are useful for detecting agentic misalignment in autonomous agents.
arXiv AI
Sep 15
Useless but Safe? Benchmarking Utility Recovery with User Intent Clarification in Multi-Turn Conversations
The paper introduces CarryOnBench, an interactive benchmark that tests whether large language models can revise their interpretation of user intent and recover utility while staying safe in multi‑turn conversations. Using 398 harmful‑looking queries with benign intents, the benchmark simulates 5,970 conversations across 14 models, evaluating both intent‑aligned utility and safety with a new metric called Ben‑Util. Results show that models often withhold information due to misinterpretation, but most can recover with clarifications, revealing failure modes such as unsafe and redundant recovery that single‑turn tests miss.
arXiv AI
Jul 14
AgentAbstain: Do LLM Agents Know When Not to Act?
arXiv:2607. 10059v1 Announce Type: new Abstract: Agent systems based on large language models (LLMs) are increasingly deployed for autonomous tasks, yet existing evaluations mostly focus on task success rather than whether agents know when to abstain.
arXiv AI
Jul 24
AppWorld-UL: Benchmarking Diverse Agent-User Interactions for Tool-Use
arXiv:2607. 20536v1 Announce Type: new Abstract: Tool-use agents that address day-to-day digital tasks such as ordering groceries must not only operate applications, but also interact with the user, e.
arXiv AI
Aug 7
Matching Matters: A Fair Quality-Efficiency Benchmark for Command-Line Agents
arXiv:2606. 21140v2 Announce Type: replace-cross Abstract: Rapid advances in large language models have improved the task-solving capabilities of command-line-interface (CLI)-based agents, whose CLIs determine how models invoke tools, maintain interaction history, and recover from failures.
arXiv AI
Aug 17
Act2Intention: A Benchmark For Developing Active Mobile Agents Through Inferring User Intention from GUI Actions
arXiv:2608. 14132v1 Announce Type: cross Abstract: Mobile GUI Agents powered by multimodal large language models (MLLMs) show promise in human-computer intelligence.
arXiv AI
Sep 16
DoubleAgents: Human-Agent Alignment in a Socially Embedded Workflow
arXiv:2509.12626v4 Announce Type: replace-cross Abstract: Aligning agentic AI with user intent is critical for delegating complex, socially embedded tasks, yet user preferences are often implicit, ev...
arXiv AI
Aug 18
Intent-Driven Situation Tracking for User-Centric Multi-Turn Agents
arXiv:2608. 15755v1 Announce Type: new Abstract: User-centric multi-turn agents must act on an evolving task situation shaped by changing user intents, accumulated tool-grounded facts, missing information, and execution constraints.