arXiv subjects

Chelsea Zou

Publications and source records attributed to Chelsea Zou.

7 recordsLinked to original sources

arXiv2026

CalBench: Evaluating Coordination-Privacy Trade-offs in Multi-Agent LLMs

Personal AI assistants are beginning to act as delegates with access to calendars, inboxes, and user preferences. Calendar scheduling makes the trust problem concrete: an assistant must coordinate with other assistants while deciding what to reveal about the person it represents. We introduce CalBench, a controlled benchmark for multi-agent calendar scheduling under private information. In each task, $N$ agents manage separate private calendars and schedule a stream of $M$ incoming meetings while minimizing disruption costs. Because no agent can inspect another agent's calendar, success requires language-mediated coordination rather than centralized planning. CalBench generates solvable scenarios with CP-SAT oracle solutions and decentralized non-LLM reference protocols, enabling evaluation of task success, excess cost, communication efficiency, burden fairness, and privacy leakage under matched information constraints. Across seven model families, we find that completion alone misses important failures: agents leave avoidable cost on the table, communication volume does not predict lower regret, and privacy-preserving silence can deprive teammates of cost information needed for fair burden allocation. CalBench provides a reproducible testbed for studying whether autonomous assistants can coordinate on behalf of users before deployment at scale.

cs.MA↗

arXiv2026

Talk is Cheap, Communication is Hard: Dynamic Grounding Failures and Repair in Multi-Agent Negotiation

Grounding is the collaborative process of establishing mutual belief sufficient for a communicative goal. While static grounding maps language to a shared context, dynamic grounding requires agents to negotiate meaning across turns. Current multi-agent Large Language Model (LLM) benchmarks largely emphasize static, one-shot tasks, overlooking whether agents can repair grounding breakdowns through interaction. We introduce an iterated multi-turn negotiation game where two agents allocate shared resources to private projects with verifiable jointly optimal outcomes. Although individual agents can identify Pareto-optimal allocations in isolation, agent dyads consistently fail to reach them across models. We identify four failure modes: (1) loss of shared interaction history, (2) stubborn anchoring to early proposals, (3) defaulting to equal splits over reward-maximizing coordination, and (4) referential binding errors across turns. Our baselines show that the coordination gap is not explained by individual reasoning limits or insufficient information exchange alone. Instead, the bottleneck lies in dynamic grounding: joint plan formation, commitment, and execution.

cs.MA↗

arXiv2025

A Unified Definition of Hallucination: It's The World Model, Stupid!

Despite numerous attempts at mitigation since the inception of language models, hallucinations remain a persistent problem even in today's frontier LLMs. Why is this? We review existing definitions of hallucination and fold them into a single, unified definition wherein prior definitions are subsumed. We argue that hallucination can be unified by defining it as simply inaccurate (internal) world modeling, in a form where it is observable to the user. For example, stating a fact which contradicts a knowledge base OR producing a summary which contradicts the source. By varying the reference world model and conflict policy, our framework unifies prior definitions. We argue that this unified view is useful because it forces evaluations to clarify their assumed reference "world", distinguishes true hallucinations from planning or reward errors, and provides a common language for comparison across benchmarks and discussion of mitigation strategies. Building on this definition, we also connect our framework to HalluWorld, a complementary benchmark that instantiates fully specified reference world models for stress-testing model hallucinations.

cs.CL↗

arXiv2025

Thinking, Faithful and Stable: Mitigating Hallucinations in LLMs

This project develops a self correcting framework for large language models (LLMs) that detects and mitigates hallucinations during multi-step reasoning. Rather than relying solely on final answer correctness, our approach leverages fine grained uncertainty signals: 1) self-assessed confidence alignment, and 2) token-level entropy spikes to detect unreliable and unfaithful reasoning in real time. We design a composite reward function that penalizes unjustified high confidence and entropy spikes, while encouraging stable and accurate reasoning trajectories. These signals guide a reinforcement learning (RL) policy that makes the model more introspective and shapes the model's generation behavior through confidence-aware reward feedback, improving not just outcome correctness but the coherence and faithfulness of their intermediate reasoning steps. Experiments show that our method improves both final answer accuracy and reasoning calibration, with ablations validating the individual contribution of each signal.

cs.AI↗

arXiv2025

Humanity's Last Exam

Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achieve over 90\% accuracy on popular benchmarks like MMLU, limiting informed measurement of state-of-the-art LLM capabilities. In response, we introduce Humanity's Last Exam (HLE), a multi-modal benchmark at the frontier of human knowledge, designed to be the final closed-ended academic benchmark of its kind with broad subject coverage. HLE consists of 2,500 questions across dozens of subjects, including mathematics, humanities, and the natural sciences. HLE is developed globally by subject-matter experts and consists of multiple-choice and short-answer questions suitable for automated grading. Each question has a known solution that is unambiguous and easily verifiable, but cannot be quickly answered via internet retrieval. State-of-the-art LLMs demonstrate low accuracy and calibration on HLE, highlighting a significant gap between current LLM capabilities and the expert human frontier on closed-ended academic questions. To inform research and policymaking upon a clear understanding of model capabilities, we publicly release HLE at https://lastexam.ai.

cs.LG↗

arXiv2024

Abstracted Gaussian Prototypes for True One-Shot Concept Learning

We introduce a cluster-based generative image segmentation framework to encode higher-level representations of visual concepts based on one-shot learning inspired by the Omniglot Challenge. The inferred parameters of each component of a Gaussian Mixture Model (GMM) represent a distinct topological subpart of a visual concept. Sampling new data from these parameters generates augmented subparts to build a more robust prototype for each concept, i.e., the Abstracted Gaussian Prototype (AGP). This framework addresses one-shot classification tasks using a cognitively-inspired similarity metric and addresses one-shot generative tasks through a novel AGP-VAE pipeline employing variational autoencoders (VAEs) to generate new class variants. Results from human judges reveal that the generative pipeline produces novel examples and classes of visual concepts that are broadly indistinguishable from those made by humans. The proposed framework leads to impressive, but not state-of-the-art, classification accuracy; thus, the contribution is two-fold: 1) the system is low in theoretical and computational complexity yet achieves the standard of 'true' one-shot learning by operating in a fully standalone manner unlike existing approaches that draw heavily on pre-training or knowledge engineering; and 2) in contrast with existing neural network approaches, the AGP approach addresses the importance of broad task capability emphasized in the Omniglot challenge (successful performance on classification and generative tasks). These two points are critical in advancing our understanding of how learning and reasoning systems can produce viable, robust, and flexible concepts based on literally no more than a single example.

cs.CV↗

arXiv2023

ARDIE: AR, Dialogue, and Eye Gaze Policies for Human-Robot Collaboration

Human-robot collaboration (HRC) has become increasingly relevant in industrial, household, and commercial settings. However, the effectiveness of such collaborations is highly dependent on the human and robots' situational awareness of the environment. Improving this awareness includes not only aligning perceptions in a shared workspace, but also bidirectionally communicating intent and visualizing different states of the environment to enhance scene understanding. In this paper, we propose ARDIE (Augmented Reality with Dialogue and Eye Gaze), a novel intelligent agent that leverages multi-modal feedback cues to enhance HRC. Our system utilizes a decision theoretic framework to formulate a joint policy that incorporates interactive augmented reality (AR), natural language, and eye gaze to portray current and future states of the environment. Through object-specific AR renders, the human can visualize future object interactions to make adjustments as needed, ultimately providing an interactive and efficient collaboration between humans and robots.

cs.RO↗