HEART-Bench evaluates LLM agents on psychological consistency using 11 Big-Five-grounded characters with 1,000 episodic memories each and 64 DIAMONDS-based decision scenarios, yielding 673 validated MCQs.
and Li, Xian , month = jun, year =
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
abstract
Large Language Model (LLM) empowered agents have recently emerged as advanced paradigms that exhibit impressive capabilities in a wide range of domains and tasks. Despite their potential, current LLM agents often adopt a one-size-fits-all approach, lacking the flexibility to respond to users' varying needs and preferences. This limitation motivates us to develop PersonaAgent, the first personalized LLM agent framework designed to address versatile personalization tasks. Specifically, PersonaAgent integrates two complementary components - a personalized memory module that includes episodic and semantic memory mechanisms; a personalized action module that enables the agent to perform tool actions tailored to the user. At the core, the persona (defined as unique system prompt for each user) functions as an intermediary: it leverages insights from personalized memory to control agent actions, while the outcomes of these actions in turn refine the memory. Based on the framework, we propose a test-time user-preference alignment strategy that simulate the latest n interactions to optimize the persona prompt, ensuring real-time user preference alignment through textual loss feedback between simulated and ground-truth responses. Experimental evaluations demonstrate that PersonaAgent significantly outperforms other baseline methods by not only personalizing the action space effectively but also scaling during test-time real-world applications. These results underscore the feasibility and potential of our approach in delivering tailored, dynamic user experiences.
years
2026 9representative citing papers
Belief Engine is a configurable belief-update mechanism for multi-agent LLM systems that uses structured argument extraction and log-odds stance updates to make evidence-grounded deliberation inspectable and controllable.
A framework called Voltron elastically distributes LLM inference across heterogeneous edge devices using layer-wise hybrid parallelism and mixed precision, achieving up to 16.5% higher accuracy than single-device execution while meeting QoS latency constraints.
RBI-Eval shows LLMs integrate sensitive memory under benign prompts at rates 8.9-82.9% higher than no-memory baselines, with retrieval systems reducing but not eliminating the effect.
PQR framework generates diverse realistic queries to elicit QA agent failures, uncovering 23-78% more unhelpful responses than prior methods in e-commerce agent tests.
RubricsTree is a scalable, evolving rubric-based evaluation system with adaptive routing that improves physician alignment for health AI responses and enables performance gains when used as feedback or rewards.
COLLEAGUE.SKILL is an open-source trace-to-skill distillation workflow that converts expert materials into portable, versioned AI skill packages with capability and bounded-behavior tracks.
On-demand runtime generation of persona-based agents can enable personalized multi-agent AI workflows beyond fixed hard-coded architectures.
Advocates prioritizing explicit contextual feedback in LLM-based recommender systems to improve user preference alignment and explainability.
citing papers explorer
-
HEART-Bench: Do LLM Agents Exhibit Human-like Psychology?
HEART-Bench evaluates LLM agents on psychological consistency using 11 Big-Five-grounded characters with 1,000 episodic memories each and 64 DIAMONDS-based decision scenarios, yielding 673 validated MCQs.
-
Belief Engine: Configurable and Inspectable Stance Dynamics in Multi-Agent LLM Deliberation
Belief Engine is a configurable belief-update mechanism for multi-agent LLM systems that uses structured argument extraction and log-odds stance updates to make evidence-grounded deliberation inspectable and controllable.
-
Voltron: Enabling Elastic Multi-Device Execution of LLM Inference for Empowered Edge Intelligence
A framework called Voltron elastically distributes LLM inference across heterogeneous edge devices using layer-wise hybrid parallelism and mixed precision, achieving up to 16.5% higher accuracy than single-device execution while meeting QoS latency constraints.
-
When Should Memory Stay Silent: Measuring Memory-Use Boundaries in Memory-Augmented Conversational Agents
RBI-Eval shows LLMs integrate sensitive memory under benign prompts at rates 8.9-82.9% higher than no-memory baselines, with retrieval systems reducing but not eliminating the effect.
-
PQR: A Framework to Generate Diverse and Realistic User Queries that Elicit QA Agent Failures
PQR framework generates diverse realistic queries to elicit QA agent failures, uncovering 23-78% more unhelpful responses than prior methods in e-commerce agent tests.
-
RubricsTree: Scalable and Evolving Open-Ended Evaluation of Personal Health Agents across Health Memory and Medical Skills
RubricsTree is a scalable, evolving rubric-based evaluation system with adaptive routing that improves physician alignment for health AI responses and enables performance gains when used as feedback or rewards.
-
COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation
COLLEAGUE.SKILL is an open-source trace-to-skill distillation workflow that converts expert materials into portable, versioned AI skill packages with capability and bounded-behavior tracks.
-
Building Persona-Based Agents On Demand: Tailoring Multi-Agent Workflows to User Needs
On-demand runtime generation of persona-based agents can enable personalized multi-agent AI workflows beyond fixed hard-coded architectures.
-
Toward User Preference Alignment in LLM Recommendation via Explicit Context Feedback
Advocates prioritizing explicit contextual feedback in LLM-based recommender systems to improve user preference alignment and explainability.