NewtonBench: Benchmarking Generalizable Scientific Law Discovery in LLM Agents

Large language models are emerging as powerful tools for scientific law discovery, a foundational challenge in AI-driven science. However, existing benchmarks for this task suffer from a fundamental methodological trilemma, forcing a trade-off between scientific relevance, scalability, and resistance to memorization. Furthermore, they oversimplify discovery as static function fitting, failing to capture the authentic scientific process of uncovering embedded laws through the interactive exploration of complex model systems. To address these critical gaps, we introduce NewtonBench, a benchmark comprising 324 scientific law discovery tasks across 12 physics domains. Our design mitigates the evaluation trilemma by using metaphysical shifts - systematic alterations of canonical laws - to generate a vast suite of problems that are scalable, scientifically relevant, and memorization-resistant. Moreover, we elevate the evaluation from static function fitting to interactive model discovery, requiring agents to experimentally probe simulated complex systems to uncover hidden principles. Our extensive experiment reveals a clear but fragile capability for discovery in frontier LLMs: this ability degrades precipitously with increasing system complexity and exhibits extreme sensitivity to observational noise. Notably, we uncover a paradoxical effect of tool assistance: providing a code interpreter can hinder more capable models by inducing a premature shift from exploration to exploitation, causing them to satisfice on suboptimal solutions. These results demonstrate that robust, generalizable discovery in complex, interactive environments remains the core challenge. By providing a scalable, robust, and scientifically authentic testbed, NewtonBench offers a crucial tool for measuring true progress and guiding the development of next-generation AI agents capable of genuine scientific discovery.

The Cognitive Bandwidth Bottleneck: Shifting Long-Horizon Agent from Planning with Actions to Planning with Schemas

Enabling LLMs to effectively operate long-horizon task which requires long-term planning and multiple interactions is essential for open-world autonomy. Conventional methods adopt planning with actions where a executable action list would be provided as reference. However, this action representation choice would be impractical when the environment action space is combinatorial exploded (e.g., open-ended real world). This naturally leads to a question: As environmental action space scales, what is the optimal action representation for long-horizon agents? In this paper, we systematically study the effectiveness of two different action representations. The first one is conventional planning with actions (PwA) which is predominantly adopted for its effectiveness on existing benchmarks. The other one is planning with schemas (PwS) which instantiate an action schema into action lists (e.g., "move [OBJ] to [OBJ]" -> "move apple to desk") to ensure concise action space and reliable scalability. This alternative is motivated by its alignment with human cognition and its compliance with environment-imposed action format restriction. We propose cognitive bandwidth perspective as a conceptual framework to qualitatively understand the differences between these two action representations and empirically observe a representation-choice inflection point between ALFWorld (~35 actions) and SciWorld (~500 actions), which serve as evidence of the need for scalable representations. We further conduct controlled experiments to study how the location of this inflection point interacts with different model capacities: stronger planning proficiency shifts the inflection rightward, whereas better schema instantiation shifts it leftward. Finally, noting the suboptimal performance of PwS agents, we provide an actionable guide for building more capable PwS agents for better scalable autonomy.

LLM-Hanabi: Evaluating Multi-Agent Gameplays with Theory-of-Mind and Rationale Inference in Imperfect Information Collaboration Game

Effective multi-agent collaboration requires agents to infer the rationale behind others' actions, a capability rooted in Theory-of-Mind (ToM). While recent Large Language Models (LLMs) excel at logical inference, their ability to infer rationale in dynamic, collaborative settings remains under-explored. This study introduces LLM-Hanabi, a novel benchmark that uses the cooperative game Hanabi to evaluate the rationale inference and ToM of LLMs. Our framework features an automated evaluation system that measures both game performance and ToM proficiency. Across a range of models, we find a significant positive correlation between ToM and in-game success. Notably, first-order ToM (interpreting others' intent) correlates more strongly with performance than second-order ToM (predicting others' interpretations). These findings highlight that for effective AI collaboration, the ability to accurately interpret a partner's rationale is more critical than higher-order reasoning. We conclude that prioritizing first-order ToM is a promising direction for enhancing the collaborative capabilities of future models.

Safety Compliance: Rethinking LLM Safety Reasoning through the Lens of Compliance

The proliferation of Large Language Models (LLMs) has demonstrated remarkable capabilities, elevating the critical importance of LLM safety. However, existing safety methods rely on ad-hoc taxonomy and lack a rigorous, systematic protection, failing to ensure safety for the nuanced and complex behaviors of modern LLM systems. To address this problem, we solve LLM safety from legal compliance perspectives, named safety compliance. In this work, we posit relevant established legal frameworks as safety standards for defining and measuring safety compliance, including the EU AI Act and GDPR, which serve as core legal frameworks for AI safety and data security in Europe. To bridge the gap between LLM safety and legal compliance, we first develop a new benchmark for safety compliance by generating realistic LLM safety scenarios seeded with legal statutes. Subsequently, we align Qwen3-8B using Group Policy Optimization (GRPO) to construct a safety reasoner, Compliance Reasoner, which effectively aligns LLMs with legal standards to mitigate safety risks. Our comprehensive experiments demonstrate that the Compliance Reasoner achieves superior performance on the new benchmark, with average improvements of +10.45% for the EU AI Act and +11.85% for GDPR.

Structuring the Unstructured: A Systematic Review of Text-to-Structure Generation for Agentic AI with a Universal Evaluation Framework

The evolution of AI systems toward agentic operation and context-aware retrieval necessitates transforming unstructured text into structured formats like tables, knowledge graphs, and charts. While such conversions enable critical applications from summarization to data mining, current research lacks a comprehensive synthesis of methodologies, datasets, and metrics. This systematic review examines text-to-structure techniques and the encountered challenges, evaluates current datasets and assessment criteria, and outlines potential directions for future research. We also introduce a universal evaluation framework for structured outputs, establishing text-to-structure as foundational infrastructure for next-generation AI systems.

Prospect Theory Fails for LLMs: Revealing Instability of Decision-Making under Epistemic Uncertainty

Prospect Theory (PT) models human decision-making under uncertainty, while epistemic markers (e.g., maybe) serve to express uncertainty in language. However, it remains largely unexplored whether Prospect Theory applies to contemporary Large Language Models and whether epistemic markers, which express human uncertainty, affect their decision-making behaviour. To address these research gaps, we design a three-stage experiment based on economic questionnaires. We propose a more general and precise evaluation framework to model LLMs' decision-making behaviour under PT, introducing uncertainty through the empirical probability values associated with commonly used epistemic markers in comparable contexts. We then incorporate epistemic markers into the evaluation framework based on their corresponding probability values to examine their influence on LLM decision-making behaviours. Our findings suggest that modelling LLMs' decision-making with PT is not consistently reliable, particularly when uncertainty is expressed in diverse linguistic forms. Our code is released in https://github.com/HKUST-KnowComp/MarPT.

SessionIntentBench: A Multi-task Inter-session Intention-shift Modeling Benchmark for E-commerce Customer Behavior Understanding

Session history is a common way of recording user interacting behaviors throughout a browsing activity with multiple products. For example, if an user clicks a product webpage and then leaves, it might because there are certain features that don't satisfy the user, which serve as an important indicator of on-the-spot user preferences. However, all prior works fail to capture and model customer intention effectively because insufficient information exploitation and only apparent information like descriptions and titles are used. There is also a lack of data and corresponding benchmark for explicitly modeling intention in E-commerce product purchase sessions. To address these issues, we introduce the concept of an intention tree and propose a dataset curation pipeline. Together, we construct a sibling multimodal benchmark, SessionIntentBench, that evaluates L(V)LMs' capability on understanding inter-session intention shift with four subtasks. With 1,952,177 intention entries, 1,132,145 session intention trajectories, and 13,003,664 available tasks mined using 10,905 sessions, we provide a scalable way to exploit the existing session data for customer intention understanding. We conduct human annotations to collect ground-truth label for a subset of collected data to form an evaluation gold set. Extensive experiments on the annotated data further confirm that current L(V)LMs fail to capture and utilize the intention across the complex session setting. Further analysis show injecting intention enhances LLMs' performances.

From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agents

Information retrieval is a cornerstone of modern knowledge acquisition, enabling billions of queries each day across diverse domains. However, traditional keyword-based search engines are increasingly inadequate for handling complex, multi-step information needs. Our position is that Large Language Models (LLMs), endowed with reasoning and agentic capabilities, are ushering in a new paradigm termed Agentic Deep Research. These systems transcend conventional information search techniques by tightly integrating autonomous reasoning, iterative retrieval, and information synthesis into a dynamic feedback loop. We trace the evolution from static web search to interactive, agent-based systems that plan, explore, and learn. We also introduce a test-time scaling law to formalize the impact of computational depth on reasoning and search. Supported by benchmark results and the rise of open-source implementations, we demonstrate that Agentic Deep Research not only significantly outperforms existing approaches, but is also poised to become the dominant paradigm for future information seeking. All the related resources, including industry products, research papers, benchmark datasets, and open-source implementations, are collected for the community in https://github.com/DavidZWZ/Awesome-Deep-Research.

Revisiting Epistemic Markers in Confidence Estimation: Can Markers Accurately Reflect Large Language Models' Uncertainty?

As large language models (LLMs) are increasingly used in high-stakes domains, accurately assessing their confidence is crucial. Humans typically express confidence through epistemic markers (e.g., "fairly confident") instead of numerical values. However, it remains unclear whether LLMs consistently use these markers to reflect their intrinsic confidence due to the difficulty of quantifying uncertainty associated with various markers. To address this gap, we first define marker confidence as the observed accuracy when a model employs an epistemic marker. We evaluate its stability across multiple question-answering datasets in both in-distribution and out-of-distribution settings for open-source and proprietary LLMs. Our results show that while markers generalize well within the same distribution, their confidence is inconsistent in out-of-distribution scenarios. These findings raise significant concerns about the reliability of epistemic markers for confidence estimation, underscoring the need for improved alignment between marker based confidence and actual model uncertainty. Our code is available at https://github.com/HKUST-KnowComp/MarCon.

AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corpora

We present AutoSchemaKG, a framework for fully autonomous knowledge graph construction that eliminates the need for predefined schemas. Our system leverages large language models to simultaneously extract knowledge triples and induce comprehensive schemas directly from text, modeling both entities and events while employing conceptualization to organize instances into semantic categories. Processing over 50 million documents, we construct ATLAS (Automated Triple Linking And Schema induction), a family of knowledge graphs with 900+ million nodes and 5.9 billion edges. This approach outperforms state-of-the-art baselines on multi-hop QA tasks and enhances LLM factuality. Notably, our schema induction achieves 95\% semantic alignment with human-crafted schemas with zero manual intervention, demonstrating that billion-scale knowledge graphs with dynamically induced schemas can effectively complement parametric knowledge in large language models.