Agent skills are procedural artifacts that enable LLM agents to execute workflows, verify constraints, and recover from failures. Existing self-evolving methods refine skills using accumulated trajectories. However, they struggle in cold-start settings, where only an initial, imperfect skill is available. Consequently, skill construction defaults to expert authoring or one-shot LLM generation. Expert-authored skills are costly and may not align with how LLM agents actually execute tasks, while one-shot generated skills can be syntactically well formed yet behaviorally weak. To bridge this gap, we propose SkillRevise, an execution-grounded framework designed to iteratively refine these initial skills. SkillRevise diagnoses skill defects from execution evidence, retrieves relevant repair principles from a general memory, and applies execution-anchored edits. By re-executing candidates and measuring empirical utility, it retains the best observed skill within the revision budget. Evaluated across three main benchmarks, two domain-specific studies, and six LLMs, SkillRevise substantially outperforms one-shot baselines—improving the base agent’s success rate on SkillsBench from 36.05% to 61.63%. Furthermore, the revised skills transfer across both executors and task environments, suggesting that SkillRevise captures reusable procedural knowledge beyond any single executor. Our code is available at https://github.com/HKUST-KnowComp/skillrevise.

Accurately assessing model confidence is essential for deploying large language models (LLMs) in mission-critical factual domains. While retrieval-augmented generation (RAG) is widely adopted to improve grounding, confidence calibration in RAG settings remains poorly understood. We conduct a systematic study across four benchmarks, revealing that LLMs exhibit poor calibration performance especially when noisy contexts are retrieved. Specifically, contradictory or irrelevant evidence tends to exacerbate the model’s overconfidence issue. To address this, we propose *NOVA Rules* (**NO**ise-aware **V**erbal Confidence C**A**Libration Rules) to provide a principled foundation for resolving overconfidence under noise. We further design **NOVA**, a noise-aware calibration framework that synthesizes supervision from ~2K HotpotQA examples guided by these rules. By performing supervised fine-tuning (SFT) with this data, NOVA equips models with intrinsic noise awareness without relying on stronger teacher models. Empirical results show that NOVA yields substantial gains, improving ECE scores by 10.9% in-domain and 8.0% out-of-domain. By bridging the gap between retrieval noise and verbal calibration, NOVA paves the way for both accurate and epistemically reliable LLMs.

While LVLMs rapidly improve, long-video question answering still remains challenging: relevant evidence is sparse, and question-relevant context often fails to provide cues that discriminate the correct answer from plausible alternatives. Diagnostic analysis on a manually annotated subset of MMR-V shows that prior agentic systems substantially improve cue retrieval over direct VLM inference yet fail to achieve a corresponding gain in answer accuracy, indicating that the bottleneck lies in option-discriminative evidence rather than topical relevance alone. We propose PACE (Progressive Acquisition of Critical Evidence), a factor-guided framework for long-video evidence acquisition. PACE proceeds in two stages: it first indexes clip-level descriptions guided by question-derived factors without observing the candidate answers; it then uses the candidate answers to derive contrastive cues and queries the index for verification. On MMR-V with the open-source Qwen3-VL backbone, PACE achieves 42.6% accuracy, outperforming direct inference and prior agentic baselines including Deep Video Discovery (DVD). On the same diagnostic subset, PACE recovers 66.9% of the annotated cues, providing empirical evidence that its gains are associated with improved evidence recovery rather than stronger answer-side priors alone. Consistent gains over DVD on LVBench, Video-MME, EgoSchema, and LongVideoBench suggest that option-aware evidence acquisition transfers beyond MMR-V.

This paper introduces **EvolvingWorld**, a framework and benchmark for character and world co-evolution in interactive literary worlds. Existing systems either treat interactive literary simulation as static persona imitation or isolated scene generation, failing to capture how characters and worlds evolve together over time. To address this, EvolvingWorld models literary simulation as a long-horizon process where characters interact, scenes progress, and character and world states are persistently updated. Unlike prior systems relying on fixed schemas, EvolvingWorld adopts an open-schema framework to support simulation across diverse literary worlds. The framework consists of two coupled modules: a **Character Agent** for multi-character role-play and persistent profile evolution, and an LLM-based **World Model** for global and location/entity-level state maintenance and scene progression. Based on this architecture, we formulate 7 trainable tasks for scene initialization, interaction generation, and state update. We construct a dataset from 57 books, producing 138,596 supervised training samples and 222 snapshots for testing. Furthermore, we introduce a trajectory-level LLM-as-Judge evaluation protocol spanning 10 dimensions and 20 metrics. Experiments show that EvolvingWorld can improve long-horizon simulation by effectively maintaining persistent, coherent character and world development.

Multimodal Large Language Models have sparked significant interest due to their potential for social intelligence; however, their ability to perform sequential motivation reasoning remains insufficiently studied. Existing evaluations predominantly examine static text or isolated visual snapshots, which do not reflect the cumulative nature of real-world behavioral drivers. To address this gap, we introduce MulTivationBench, a benchmark designed to rigorously evaluate multimodal motivation reasoning within story-driven visual narratives. The benchmark builds upon established psychological frameworks—Maslow’s hierarchy and Reiss’s basic desires—and requires models to integrate accumulated multimodal context to infer evolving motivations. Results indicate that MulTivationBench presents a significant challenge: all tested models struggle to maintain consistent motivation reasoning across sequential contexts, revealing a critical disconnect between static recognition capabilities and the dynamic reasoning essential for human-like social 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.

Real-world decision-making often involves uncertainty expressed in linguistic rather than numerical terms, and Prospect Theory (PT) provides a classic framework for modeling human behavior under such uncertainty. Although recent studies have developed frameworks to estimate PT parameters for Large Language Models (LLMs), few have examined whether PT itself adequately describes LLM decision-making behavior. To address these gaps, we develop a streamlined workflow grounded in a classic behavioral economics experimental paradigm. First, we estimate PT parameters and evaluate how well the resulting model captures LLM decision-making behavior. We then derive probability mappings for epistemic markers in the same context and inject them into prompts to examine the stability of PT parameters under linguistic uncertainty. Our findings suggest that PT does not consistently provide a reliable account of LLM decision-making across models, and that its application to LLMs is likely sensitive to epistemic uncertainty. The findings caution against the deployment of PT-based frameworks in real-world applications where epistemic ambiguity is prevalent, giving valuable insights in behaviour interpretation and future alignment direction for LLM decision-making.

LLM agents increasingly operate in large tool ecosystems, where real-world tasks require discovering relevant tools, inferring implicit sub-goals, and adapting to dynamic environments over long horizons. However, existing benchmarks rarely evaluate planning under retrieval-limited tool visibility. To address this gap, we introduce **PlanBench-XL**, an interactive benchmark of 327 retail tasks over 1,665 tools that tests whether agents can iteratively retrieve usable tools, invoke them to uncover intermediate evidence for subsequent calls toward the final goal. PlanBench-XL further features an optional blocking mechanism that simulates real-world unpredictability through missing, failing, or distracting tool functions, forcing agents to detect disrupted paths and adapt at runtime. Experiments on ten leading LLMs show that massive-tool planning remains challenging: while GPT-5.4 achieves 51.90% accuracy in block-free settings, it collapses to 11.36% under the most severe blocking condition. Further analysis shows that agents are especially vulnerable when failures lack explicit error signals or when recovery requires longer alternative tool-use paths. These results establish PlanBench-XL as a testbed for diagnosing agentic planning failures and highlight the need for robust adaptive planning in long-horizon tasks with large, imperfect tool environments.

Multimodal abductive reasoning — the generation and selection of explanatory hypotheses from partial observations — is a cornerstone of intelligence. Current evaluations of such ability in vision–language models (VLMs) are largely confined to static, single-agent tasks. Inspired by Dixit, we introduce DixitWorld, a comprehensive evaluation suite designed to deconstruct this challenge. DixitWorld features two core components: DixitArena, a dynamic, multi-agent environment that evaluates both hypothesis generation (a “storyteller” crafting cryptic clues) and hypothesis selection (“listeners” choosing the target image from decoys) under imperfect information; and DixitBench, a static QA benchmark that isolates the listener’s task for efficient, controlled evaluation. Results from DixitArena reveal distinct, role-dependent behaviors: smaller open-source models often excel as creative storytellers, producing imaginative yet less discriminative clues, whereas larger proprietary models demonstrate superior overall performance, particularly as listeners. Performance on DixitBench strongly correlates with listener results in DixitArena, validating it as a reliable proxy for hypothesis selection. Our findings reveal a key trade-off between generative creativity and discriminative understanding in multimodal abductive reasoning, a central challenge for developing more balanced and capable vision-language agents.

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 92% 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.

Current evaluations of Large Language Model (LLM) agents primarily emphasize task completion, often overlooking resource efficiency and adaptability. This neglects a crucial capability: agents’ ability to devise and adjust cost-optimal plans in response to changing environments. To bridge this gap, we introduce CostBench, a scalable, cost-centric benchmark designed to evaluate agents’ economic reasoning and replanning abilities. Situated in the travel-planning domain, CostBench comprises tasks solvable via multiple sequences of atomic and composite tools with diverse, customizable costs. It also supports four types of dynamic blocking events, such as tool failures and cost changes, to simulate real-world unpredictability and necessitate agents to adapt in real time. Evaluating leading open-sourced and proprietary models on CostBench reveals a substantial gap in cost-aware planning: agents frequently fail to identify cost-optimal solutions in static settings, with even GPT-5 achieving less than 75% exact match rate on the hardest tasks, and performance further drops significantly under dynamic conditions. By diagnosing these weaknesses, CostBench lays the groundwork for developing future agents that are both economically rational and robust.

The rapid development of LLMs has sparked extensive research into their factual knowledge. Current works find that LLMs fall short on questions around low-frequency entities. However, such proofs are unreliable since the questions can differ not only in entity frequency but also in difficulty themselves. So we introduce ComparisonQA benchmark, containing 283K abstract questions, each instantiated by a pair of high-frequency and low-frequency entities. It ensures a controllable comparison to study the role of knowledge frequency in the performance of LLMs. Because the difference between such a pair is only the entity with different frequencies. In addition, we use both correctness and uncertainty to develop a two-round method to evaluate LLMs’ knowledge robustness. It aims to avoid possible semantic shortcuts which is a serious problem of current QA study. Experiments reveal that LLMs, including GPT-4o, exhibit particularly low robustness regarding low-frequency knowledge. Besides, we find that uncertainty can be used to effectively identify high-quality and shortcut-free questions while maintaining the data size. Based on this, we propose an automatic method to select such questions to form a subset called ComparisonQA-Hard, containing only hard low-frequency questions.

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.

Dialogue Argument Mining(DialAM) is an important branch of Argument Mining(AM). DialAM-2024 is a shared task focusing on dialogue argument mining, which requires us to identify argumentative relations and illocutionary relations among proposition nodes and locution nodes. To accomplish this, we propose a two-stage pipeline, which includes the Two-Step S-Node Prediction Model in Stage 1 and the YA-Node Prediction Model in Stage 2. We also augment the training data in both stages and introduce context in the prediction of Stage 2. We successfully completed the task and achieved good results. Our team KNOWCOMP POKEMON ranked 1st in the ARI Focused score and 4th in the Global Focused score.

Abstraction ability is crucial in human intelligence, which can also benefit various tasks in NLP study. Existing work shows that LLMs are deficient in abstract ability, and how to improve it remains unexplored. In this work, we design the framework AbsInstruct to enhance LLMs’ abstraction ability through instruction tuning. The framework builds instructions with in-depth explanations to assist LLMs in capturing the underlying rationale of abstraction. Meanwhile, we introduce a plausibility estimator to select instructions that are more consistent with the abstraction knowledge of LLMs to be aligned. Then, our framework combines abstraction instructions with general-purpose ones to build a hybrid dataset. Extensive experiments and analyses demonstrate that our framework can considerably enhance LLMs’ abstraction ability with strong generalization performance while maintaining their general instruction-following abilities.

Sign Language Translation (SLT) is a complex task that involves accurately interpreting sign language gestures and translating them into spoken or written language and vice versa. Its primary objective is to facilitate communication between individuals with hearing difficulties using deep learning systems. Existing approaches leverage gloss annotations of sign language gestures to assist the model in capturing the movement and differentiating various gestures. However, constructing a large-scale gloss-annotated dataset is both expensive and impractical to cover multiple languages, and pre-trained generative models cannot be efficiently used due to the lack of textual source context in SLT. To address these challenges, we propose a gloss-free framework for the WMT23 SLT task. Our system primarily consists of a visual extractor for extracting video embeddings and a generator responsible for producing the translated text. We also employ an embedding alignment block that is trained to align the embedding space of the visual extractor with that of the generator. Despite undergoing extensive training and validation, our system consistently falls short of meeting the baseline performance. Further analysis shows that our model’s poor projection rate prevents it from learning diverse visual embeddings. Our codes and model checkpoints are available at https://github.com/HKUST-KnowComp/SLT.

A main goal of Argument Mining (AM) is to analyze an author’s stance. Unlike previous AM datasets focusing only on text, the shared task at the 10th Workshop on Argument Mining introduces a dataset including both texts and images. Importantly, these images contain both visual elements and optical characters. Our new framework, TILFA (A Unified Framework for Text, Image, and Layout Fusion in Argument Mining), is designed to handle this mixed data. It excels at not only understanding text but also detecting optical characters and recognizing layout details in images. Our model significantly outperforms existing baselines, earning our team, KnowComp, the 1st place in the leaderboard of Argumentative Stance Classification subtask in this shared task.

We participate in the LT4HALA2022 shared task EvaHan. This task has two subtasks. Subtask 1 is word segmentation, and subtask 2 is part-of-speech tagging. Each subtask consists of two tracks, a close track that can only use the data and models provided by the organizer, and an open track without restrictions. We employ three pre-trained models, two of which are open-source pre-trained models for ancient Chinese (Siku-Roberta and roberta-classical-chinese), and one is our pre-trained GlyphBERT combined with glyph features. Our methods include data augmentation, data pre-processing, model pretraining, downstream fine-tuning, k-fold cross validation and model ensemble. We achieve competitive P, R, and F1 scores on both our own validation set and the final public test set.