Make Any Collection Navigable: Methods for Constructing and Evaluating Hypergraph of Text

One reason the Web is more useful than a simple collection of documents is that the structure created by hyperlinks enables flexible navigation from one web page to another. However, hyperlinks are typically created manually and cannot fully capture a corpus' implicit semantic structures. Is there a general way to make an arbitrary collection navigable? Recent work has formalized this problem generally as constructing a Hypergraph of Text (HoT), which provides a formal mathematical structure for supporting navigation and browsing. However, how to construct and evaluate a Hypergraph of Text remains a challenge. In this paper, we propose and study several methods for constructing a HoT. We also propose a novel quantitative metric, effort ratio, for evaluating the structural quality of a constructed HoT. Experimental results show that even simple TF-IDF baselines can match LLM-based methods on our proposed effort ratio metric.

An Axiomatic Benchmark for Evaluation of Scientific Novelty Metrics

The rigorous evaluation of the novelty of a scientific paper is, even for human scientists, a challenging task. With the increasing interest in AI scientists and AI involvement in scientific idea generation and paper writing, it also becomes increasingly important that this task be automatable and reliable, lest both human attention and compute tokens be wasted on ideas that have already been explored. Due to the challenge of quantifying ground-truth novelty, however, existing novelty metrics for scientific papers generally validate their results against noisy, confounded signals such as citation counts or peer review scores. These proxies can conflate novelty with impact, quality, or reviewer preference, which in turn makes it harder to assess how well a given metric actually evaluates novelty. We therefore propose an axiomatic benchmark for scientific novelty metrics. We first define a set of axioms that a well-behaved novelty metric should satisfy, grounded in human scientific norms and practice, then evaluate existing metrics across ten tasks spanning three domains of AI research. Our results reveal that no existing metric satisfies all axioms consistently, and that metrics fail on systematically different axioms, reflecting their underlying architectures. Additionally, we show that combining metrics of complementary architectures leads to consistent improvements on the benchmark, with per-axiom weighting achieving 90.1% versus 71.5% for the best individual metric, suggesting that developing architecturally diverse metrics is a promising direction for future work. We release the benchmark code as supplementary material to encourage the development of more robust scientific literature novelty metrics.

Benchmarking Multi-turn Medical Diagnosis: Hold, Lure, and Self-Correction

Large language models (LLMs) achieve high accuracy in medical diagnosis when all clinical information is provided in a single turn, yet how they behave under multi-turn evidence accumulation closer to real clinical reasoning remains unexplored. We introduce MINT (Medical Incremental N-Turn Benchmark), a high-fidelity, multi-turn medical diagnosis benchmark comprising 1,035 cases with clinically labeled evidence shards, controlled turn granularity, and information-preserving decomposition. Through systematic evaluation of 11 LLMs on MINT, we uncover three persistent behavioral patterns that significantly impact diagnostic decisions: (1) intent to answer, models rush to answer before sufficient evidence has been observed, with over 55% of answers committed within the first two turns; (2) self-correction, incorrect-to-correct answer revisions occur at up to 10.6 times the rate of correct-to-incorrect flips, revealing a latent capacity for self-correction that premature commitment forecloses; and (3) strong lures, clinically salient information such as laboratory results trigger premature answering even when models are explicitly instructed to wait. We translate these findings into clinically actionable guidance: deferring the diagnostic question to later turns reduces premature answering and improves accuracy at the first point of commitment by up to 62.6%, while reserving salient clinical evidence for later turns prevents a catastrophic accuracy drop of up to 23.3% caused by premature commitment. Our work provides both a controlled evaluation framework and concrete recommendations for improving the reliability of LLMs in multi-turn medical diagnosis.

User Preference Modeling for Conversational LLM Agents: Weak Rewards from Retrieval-Augmented Interaction

Large language models are increasingly used as personal assistants, yet most lack a persistent user model, forcing users to repeatedly restate preferences across sessions. We propose Vector-Adapted Retrieval Scoring (VARS), a pipeline-agnostic, frozen-backbone framework that represents each user with long-term and short-term vectors in a shared preference space and uses these vectors to bias retrieval scoring over structured preference memory. The vectors are updated online from weak scalar rewards from users' feedback, enabling personalization without per-user fine-tuning. We evaluate on \textsc{MultiSessionCollab}, an online multi-session collaboration benchmark with rich user preference profiles, across math and code tasks. Under frozen backbones, the main benefit of user-aware retrieval is improved interaction efficiency rather than large gains in raw task accuracy: our full VARS agent achieves the strongest overall performance, matches a strong Reflection baseline in task success, and reduces timeout rate and user effort. The learned long-term vectors also align with cross-user preference overlap, while short-term vectors capture session-specific adaptation, supporting the interpretability of the dual-vector design. Code, model, and data are available at https://github.com/YurenHao0426/VARS.

ERA: Transforming VLMs into Embodied Agents via Embodied Prior Learning and Online Reinforcement Learning

Recent advances in embodied AI highlight the potential of vision language models (VLMs) as agents capable of perception, reasoning, and interaction in complex environments. However, top-performing systems rely on large-scale models that are costly to deploy, while smaller VLMs lack the necessary knowledge and skills to succeed. To bridge this gap, we present \textit{Embodied Reasoning Agent (ERA)}, a two-stage framework that integrates prior knowledge learning and online reinforcement learning (RL). The first stage, \textit{Embodied Prior Learning}, distills foundational knowledge from three types of data: (1) Trajectory-Augmented Priors, which enrich existing trajectory data with structured reasoning generated by stronger models; (2) Environment-Anchored Priors, which provide in-environment knowledge and grounding supervision; and (3) External Knowledge Priors, which transfer general knowledge from out-of-environment datasets. In the second stage, we develop an online RL pipeline that builds on these priors to further enhance agent performance. To overcome the inherent challenges in agent RL, including long horizons, sparse rewards, and training instability, we introduce three key designs: self-summarization for context management, dense reward shaping, and turn-level policy optimization. Extensive experiments on both high-level planning (EB-ALFRED) and low-level control (EB-Manipulation) tasks demonstrate that ERA-3B surpasses both prompting-based large models and previous training-based baselines. Specifically, it achieves overall improvements of 8.4\% on EB-ALFRED and 19.4\% on EB-Manipulation over GPT-4o, and exhibits strong generalization to unseen tasks. Overall, ERA offers a practical path toward scalable embodied intelligence, providing methodological insights for future embodied AI systems.

Do Role-Playing Agents Practice What They Preach? Belief-Behavior Consistency in LLM-Based Simulations of Human Trust

As LLMs are increasingly studied as role-playing agents to generate synthetic data for human behavioral research, ensuring that their outputs remain coherent with their assigned roles has become a critical concern. In this paper, we investigate how consistently LLM-based role-playing agents' stated beliefs about the behavior of the people they are asked to role-play ("what they say") correspond to their actual behavior during role-play ("how they act"). Specifically, we establish an evaluation framework to rigorously measure how well beliefs obtained by prompting the model can predict simulation outcomes in advance. Using an augmented version of the GenAgents persona bank and the Trust Game (a standard economic game used to quantify players' trust and reciprocity), we introduce a belief-behavior consistency metric to systematically investigate how it is affected by factors such as: (1) the types of beliefs we elicit from LLMs, like expected outcomes of simulations versus task-relevant attributes of individual characters LLMs are asked to simulate; (2) when and how we present LLMs with relevant information about Trust Game; and (3) how far into the future we ask the model to forecast its actions. We also explore how feasible it is to impose a researcher's own theoretical priors in the event that the originally elicited beliefs are misaligned with research objectives. Our results reveal systematic inconsistencies between LLMs' stated (or imposed) beliefs and the outcomes of their role-playing simulation, at both an individual- and population-level. Specifically, we find that, even when models appear to encode plausible beliefs, they may fail to apply them in a consistent way. These findings highlight the need to identify how and when LLMs' stated beliefs align with their simulated behavior, allowing researchers to use LLM-based agents appropriately in behavioral studies.

Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation

Given the growing influence of language model-based agents on high-stakes societal decisions, from public policy to healthcare, ensuring their beneficial impact requires understanding the far-reaching implications of their suggestions. We propose a proof-of-concept framework that projects how model-generated advice could propagate through societal systems on a macroscopic scale over time, enabling more robust alignment. To assess the long-term safety awareness of language models, we also introduce a dataset of 100 indirect harm scenarios, testing models' ability to foresee adverse, non-obvious outcomes from seemingly harmless user prompts. Our approach achieves not only over 20% improvement on the new dataset but also an average win rate exceeding 70% against strong baselines on existing safety benchmarks (AdvBench, SafeRLHF, WildGuardMix), suggesting a promising direction for safer agents.

Ten Principles of AI Agent Economics

The rapid rise of AI-based autonomous agents is transforming human society and economic systems, as these entities increasingly exhibit human-like or superhuman intelligence. From excelling at complex games like Go to tackling diverse general-purpose tasks with large language and multimodal models, AI agents are evolving from specialized tools into dynamic participants in social and economic ecosystems. Their autonomy and decision-making capabilities are poised to impact industries, professions, and human lives profoundly, raising critical questions about their integration into economic activities, potential ethical concerns, and the balance between their utility and safety. To address these challenges, this paper presents ten principles of AI agent economics, offering a framework to understand how AI agents make decisions, influence social interactions, and participate in the broader economy. Drawing on economics, decision theory, and ethics, we explore fundamental questions, such as whether AI agents might evolve from tools into independent entities, their impact on labor markets, and the ethical safeguards needed to align them with human values. These principles build on existing economic theories while accounting for the unique traits of AI agents, providing a roadmap for their responsible integration into human systems. Beyond theoretical insights, this paper highlights the urgency of future research into AI trustworthiness, ethical guidelines, and regulatory oversight. As we enter a transformative era, this work serves as both a guide and a call to action, ensuring AI agents contribute positively to human progress while addressing risks tied to their unprecedented capabilities.

User Simulation in the Era of Generative AI: User Modeling, Synthetic Data Generation, and System Evaluation

User simulation is an emerging interdisciplinary topic with multiple critical applications in the era of Generative AI. It involves creating an intelligent agent that mimics the actions of a human user interacting with an AI system, enabling researchers to model and analyze user behaviour, generate synthetic data for training, and evaluate interactive AI systems in a controlled and reproducible manner. User simulation has profound implications for diverse fields and plays a vital role in the pursuit of Artificial General Intelligence. This paper provides an overview of user simulation, highlighting its key applications, connections to various disciplines, and outlining future research directions to advance this increasingly important technology.

Interactive Information Need Prediction with Intent and Context

The ability to predict a user's information need would have wide-ranging implications, from saving time and effort to mitigating vocabulary gaps. We study how to interactively predict a user's information need by letting them select a pre-search context (e.g., a paragraph, sentence, or singe word) and specify an optional partial search intent (e.g., "how", "why", "applications", etc.). We examine how various generative language models can explicitly make this prediction by generating a question as well as how retrieval models can implicitly make this prediction by retrieving an answer. We find that this prediction process is possible in many cases and that user-provided partial search intent can help mitigate large pre-search contexts. We conclude that this framework is promising and suitable for real-world applications.