Searcharxiv⌕ Search

arXiv subjects

See-Kiong Ng

Publications and source records attributed to See-Kiong Ng.

At least 19 recordsLinked to original sources
arXiv2026

Clearing the Fog: Towards Installing and Refining Proactive Exploration Capabilities in LLM Agents

We study proactive exploration in LLM agents, i.e., the ability to explore an environment to acquire information that improves future decision-making. In this regard, we first identify two fundamental bottlenecks that hinder this capability and then propose \ours, a novel method designed to instill and refine proactive exploration. Specifically, \ours\ consists of two components: (1) Exploratory Data Construction, which synthesizes exploration-rich trajectories to mitigate the hindsight bias of standard demonstrations; and (2) RL Optimization with Contrastive Signal Guidance, which leverages contrastive trajectory pairs to distinguish productive exploration from redundant wandering. Extensive experiments demonstrate the effectiveness of \ours\ and provide insights into the characteristics of proactive exploration. Our code is available at: https://github.com/GuanZhizhao/SAFARI.

cs.AI↗
arXiv2026

Empowering VLMs for Few-Shot Multimodal Time Series Classification via Tailored Agentic Reasoning

In this paper, we propose the first VL\underline{\textbf{M}} \underline{\textbf{a}}gentic \underline{\textbf{r}}easoning framework for few-\underline{\textbf{s}}hot multimodal \underline{\textbf{T}}ime \underline{\textbf{S}}eries \underline{\textbf{C}}lassification (\textsc{MarsTSC}), which introduces a self-evolving knowledge bank as a dynamic context iteratively refined via reflective agentic reasoning. The framework comprises three collaborative roles: i) Generator conducts reliable classification via reasoning; ii) Reflector diagnoses the root causes of reasoning errors to yield discriminative insights targeting the temporal features overlooked by Generator; iii) Modifier applies verified updates to the knowledge bank to prevent context collapse. We further introduce a test-time update strategy to enable cautious, continuous knowledge bank refinement to mitigate few-shot bias and distribution shift. Extensive experiments across 12 mainstream time series benchmark datasets demonstrate that \method{} delivers substantial and consistent performance gains across 5 VLM backbones, outperforming both classical and foundation model-based time series baselines under few-shot conditions, while producing interpretable rationales that ground each classification decision in human-readable feature evidence. Code is available at https://github.com/HuangJW0821/MarsTSC.

cs.AI↗
arXiv2026

GLOW: Graph-Language Co-Encoding for Agentic Workflow Performance Prediction

Agentic Workflows (AWs) have emerged as a promising paradigm for solving complex tasks. However, automatically generating high-quality AWs remains expensive because AW optimization requires evaluating a large number of candidate AWs via execution, resulting in high computational cost and latency. Recently, AW performance prediction has become a hot research topic to avoid costly execution-based evaluation, but existing methods primarily use Graph Neural Networks (GNNs) to model workflow structures and insufficiently capture the semantic relationships among agents. To address this limitation, we propose GLOW, a unified framework for AW performance prediction that combines the graph-structure modeling ability of GNNs with the topology-aware semantic encoding capability of LLMs. Specifically, a graph-oriented LLM is first built through instruction-tuning on graph understanding tasks to extract topology-aware semantic representations from descriptive text of AWs. Meanwhile, a GNN explicitly models the structural information of AWs and produces corresponding structural representations. The semantic and structural representations are then fused in a shared latent space using a Transformer-based fusion module. A contrastive learning strategy is further introduced to learn more discriminative representations for AWs. Experiments on the FLORA-Bench benchmark demonstrate that GLOW consistently outperforms state-of-the-art baselines in both prediction accuracy and ranking utility. Moreover, when integrated into the AFLOW, an automatic AW generation framework, GLOW reduces optimization time by 98.7% with only a 0.031 average score decrease across three datasets, showing its effectiveness as an efficient surrogate evaluator for AW optimization.

cs.LG↗
arXiv2026

Towards Effective Structured Context Modeling for Conversational Recommender Systems via Dual-node Monte Carlo Tree Search

We investigate the role of conversational context modeling in user preference tracking for Conversational Recommendation Systems (CRSs). In this regard, we propose DREAMS, a novel tree-structured context modeling framework that explicitly captures user preference evolution throughout multi-turn interactions. DREAMS introduces two specialized node types to support the two fundamental objectives of CRSs: preference elicitation and preference exploitation. Specifically, elicitation nodes leverage Monte Carlo Tree Search (MCTS) to strategically explore conversational actions and infer latent user preferences, while exploitation nodes employ LLM-based refinement to transform the tracked preference state into structured retrieval queries for recommendation. Extensive experiments on benchmark datasets demonstrate the effectiveness of DREAMS and its design.

cs.IR↗
arXiv2026

Measuring the Checker: Mutation Analysis for GPU-Kernel Benchmark Oracles

Benchmarks for LLM-generated GPU kernels decide correctness with a few random inputs and a loose floating-point tolerance, and their verdicts now feed leaderboards and reinforcement-learning rewards. Recent work agrees these checkers are weak and patches them by hand---extra input distributions, fuzzing recipes, tighter tolerances---with no way to \emph{measure} whether any patch suffices. We introduce mutation analysis as an adequacy metric for kernel-benchmark oracles: deterministic rules inject 10{,}303 compilable faults into verified CUDA implementations of 188 KernelBench problems, 7{,}384 of them with an independent kill witness; any test protocol is scored by the fraction it detects. The official check misses \textbf{one in six} witnessed faults (16.9%), deterministically, and the misses are skewed by family: 8.7% of arithmetic faults escape, but 78.6% of precision faults do. The metric explains why (a tolerance blind band growing with reduction size; a measured ceiling on input aggressiveness set by legitimate floating-point variance), audits the strongest existing patch (KernelBench-Verified's gain splits into $+4.0$ points from hidden inputs and $+4.5$ from tighter tolerance, a split its authors could not compute), and exposes a published fuzzing recipe that rejects \emph{correct} kernels 107 times. Optimizing suites over the kill matrix reaches 98.0% detection with two inputs per problem (94.8% held-out), and the measurement's fault taxonomy teaches a test generator more than the raw faults themselves. Across 48 whole architectures, the blindness grows with scale, concentrating in deep homogeneous pipelines, and two problems prove unrefereeable: their official references violate the benchmark's own tolerance against fp64. We release everything as \href{https://huggingface.co/datasets/Elfsong/KernelBench-M}{KernelBench-M}.

cs.LG↗
arXiv2026

FineVerify: Scaling Test-Time Compute with Fine-Grained Self-Verification for Agentic Search

Agentic search requires language model agents to explore many sources and answer complex information-seeking questions. Scaling test-time compute is a promising way to improve these agents, but current approaches can fail, because correct answers are often sparse and score-based selection depends on model calibration. We propose FineVerify, a fine-grained self-verification framework that decomposes each question into checkable sub-questions, verifies sampled candidates against each sub-question, and selects the candidate with the highest aggregated score. This per-check structure turns selection into simpler local judgments and produces scores under the same explicit criteria. Across four agentic search benchmarks and two models, FineVerify consistently outperforms standard scaling baselines. With only four sampled trajectories, it improves GPT-5-mini by 8.2 accuracy points and Gemini-3-flash by 5.6% on average. With 12 samples, FineVerify enables GPT-5-mini to surpass frontier GPT-5 on BrowseComp-Plus. Beyond accuracy, FineVerify produces interpretable verification traces that help audit benchmark errors, suggesting broader applications for inspecting agentic search systems. Code and data are available at https://github.com/XuZhao0/fineverify

cs.CL↗
arXiv2026

Self-Evolving World Models for LLM Agent Planning

World models offer a principled way to equip long-horizon LLM agents with foresight: predictions of action consequences before execution. However, unreliable foresight can be ignored, misused, or even degrade downstream decision-making. In this paper, we introduce WorldEvolver, a self-evolving world model framework that revises its deployment-time context while keeping the downstream agent and all model parameters frozen. WorldEvolver integrates three modules: (i) Episodic Memory, which exploits real action transitions through retrieval-based simulation; (ii) Semantic Memory, which extracts persistent heuristic rules from prediction-observation mismatches; and (iii) Selective Foresight, which filters low-confidence predictions before integrating them into agent reasoning context. We evaluate WorldEvolver on ALFWorld and ScienceWorld, measuring world model prediction accuracy on Word2World and downstream agent success rate on AgentBoard. Extensive experiments show that WorldEvolver achieves the highest prediction accuracy across three backbones and leads other world model baselines on downstream agent success rate, demonstrating that test-time memory revision enhances both predictive fidelity and planning performance.

cs.AI↗
arXiv2026

MatReplace: A Reference-Free, Conditioning-Aligned Benchmark for Material Replacement in Interior Scenes

Material replacement is a common interior-design operation: changing the material of a selected surface while preserving its geometry, surroundings, and illumination. Despite its commercial relevance, no public benchmark isolates this task, and evaluating it is challenging. Reference-based metrics penalize valid outputs in this inherently one-to-many setting, favor the style of the reference generator, and cannot fairly compare editors that receive different forms of guidance. We introduce MatReplace, a reference-free benchmark that evaluates edits along four verifiable dimensions: local material correctness, global lighting harmony, outside preservation, and inside structure. It defines three tracks that vary one conditioning signal at a time: (A) instruction only, (B) instruction plus region mask, and (C) material reference image instead of instruction. Our results reveal a clear divide between naming and visually grounding materials. In Track A, leading closed-source editors achieve exemplar-level material rendering and surpass the exemplar anchor under our primary aggregate. In Track B, masks help only mask-compatible models with weak scene preservation, with task-paired, single-seed effects ranging from +0.137 to -0.090 across aligned model families. In Track C, reference-image conditioning degrades every family under both aggregates, by -0.031 to -0.508; in the worst cases, models repaint the reference image itself and perform worse than returning the input unchanged. Thus, named-material rendering is largely solved by the strongest closed editors on this distribution, but grounding materials from pixels remains an open challenge. Expert ratings validate our ranking (Kendall's tau = 0.68) and align with our aggregates more closely than GT-referenced or CLIP-based baselines.

cs.CV↗
arXiv2026

ExpConCAD: Experience-Guided Text-to-CAD Generation from Shape Descriptions with Implicit Spatial Constraints

Text-to-CAD aims to generate executable CAD programs from natural-language descriptions. However, real-world descriptions are often underspecified and omit critical spatial constraints required for valid CAD construction, a challenge that has been largely overlooked by existing methods. In this paper, we argue that missing spatial constraints should be inferred with respect to the underlying construction structure and informed by reusable design experience. Based on this insight, we propose ExpConCAD, an experience-enhanced framework for implicit spatial constraint completion. ExpConCAD first recovers the intended construction structure and constraint scopes, then retrieves relevant constraint-completion experience for similar scopes to complete the missing spatial constraints, and finally generates executable CadQuery programs. Extensive experiments demonstrate the effectiveness of ExpConCAD and provide insights into the role of construction structure understanding and experience memory in spatial constraint completion. Our code is available at: https://github.com/Hotjiashell/ExpConCAD.

cs.CL↗
arXiv2026

Towards Faithful Simulation of Human Shopping Behavior

Simulating realistic user shopping behavior underpins offline evaluation and reinforcement learning in e-commerce scenarios. While recent LLM- and VLM-based simulators have made encouraging progress, reproducing a real browsing session remains difficult for two reasons. (i) Memory Challenge: a shopping session spans dozens of pages, yet existing agents either discard long-range observation histories, losing the evolving user state, or naively concatenate them, overwhelming the context window and even degrading simulation quality. (ii) Optimization Challenge: current user simulators are typically supervised to match each logged action via imitation or step-level rewards; the resulting sessions often display unrealistic patterns, such as over-exploration or excessive passivity, which per-step supervision can neither detect nor correct. To address the above challenges, we present RecVerse, a GUI-grounded simulation agent that perceives pages through screenshots and produces faithful multi-turn trajectories. For the memory challenge, RecVerse adopts a cognitive-inspired hierarchical memory: Working Memory for short-term focus, Episodic Memory for in-session traces, and Preference Memory for high-level intent, with memory updates treated as actions so that the agent adaptively learns when and what to memorize. For the optimization challenge, RecVerse is optimized with a trajectory-level RL objective that scores entire sessions, aligning both macro-level action-type distributions and micro-level shopping intent with real users. We further release USB (User Simulation Benchmark), an interactive e-commerce GUI trajectory dataset for multi-turn user simulation. Experiments show that RecVerse significantly outperforms existing baselines in both behavioral fidelity and intent consistency.

cs.IR↗
arXiv2026

Tracking the Truth: Object-Centric Spatio-Temporal Monitoring for Video Large Language Models

While multimodal large language models (MLLMs) have advanced video understanding, they remain highly prone to hallucinations in dynamic scenes. We argue this stems from a failure in spatio-temporal monitoring, the ability to persistently track object identities, states, and relations over time. Existing benchmarks obscure this deficit by relying on single final-answer evaluations for queries that can often be resolved via local visual cues or statistical priors. To rigorously diagnose this, we introduce STEMO-Bench (Spatio-TEmporal MOnitoring), a benchmark of human-verified object-centric facts that evaluates intermediate reasoning by decomposing queries into sub-questions, distinguishing genuine temporal understanding from coincidental correctness. To address failure modes exposed by STEMO, we propose STEMO-Track, a novel object-centric framework that explicitly constructs and reasons over structured object trajectories via chunk-wise state extraction and temporal aggregation. Extensive experiments demonstrate that our object-centric framework significantly reduces hallucinated answers and improves spatio-temporal reasoning consistency over state-of-the-art MLLMs.

cs.CV↗
arXiv2026

Multilingual Agent-Based World Modeling for Social Science

Multi-agent role-playing has recently shown promise for studying social behavior with language agents, but existing simulations are mostly monolingual without cross-lingual interaction, an essential property of real societies. We introduce MAWM, the first Multilingual Agent-based World Modeling framework that supports multi-turn multilingual interactions among generative agents with diverse sociolinguistic profiles. MAWM enables two modes of analysis: (i) global public opinion modeling, which tracks how attitudes toward open-domain survey questions evolve across languages and cultures, and (ii) media influence and information diffusion, via autonomous news agents that dynamically generate content and shape user behavior. To ground the simulation in realistic population distributions, we construct the MAPS benchmark, which combines survey questions and demographic personas drawn from global population distributions. Experiments on simulation alignment, along with social science case studies on cultural assimilation and normative diffusion, show that native-language simulation better reflects real survey data than English-only simulation, and that the agent society in MAWM reproduces established sociocultural phenomena and highlights the value of multilingual simulation as an alternative interpretable tool for computational social science.

cs.CL↗
arXiv2026

Test-Time Scaling in Reasoning Models Is Not Effective for Knowledge-Intensive Tasks Yet

Test-time scaling increases inference-time computation through longer reasoning chains and has shown strong performance gains across many domains. However, frontier models still suffer from factuality hallucinations, raising the question of whether increased computation is effective on closed-book knowledge-intensive tasks. In this work, we evaluate 14 reasoning models under different test-time scaling strategies. Our results challenge its effectiveness: increasing test-time computation does not consistently improve accuracy and often leads to more hallucinations. We find that changes in hallucination rates are largely driven by the model's willingness to answer, as longer reasoning encourages more attempts, many of which are incorrect. We also observe patterns consistent with confirmation bias, where extended reasoning reinforces early incorrect beliefs with fabricated details. Finally, we provide an information-theoretic perspective showing that compute-only test-time scaling, as a post-processing procedure of a fixed model, cannot introduce new information about the ground-truth answer, explaining the limited performance gains. Overall, our findings highlight important limitations of current test-time scaling methods for closed-book knowledge-intensive tasks. Code and data are available at https://github.com/XuZhao0/tts-knowledge

cs.AI↗
arXiv2026

DynaPix: Can Vision-Language Models Identify the Exact Future?

Acting in a physical scene requires knowing its real later state, not a plausible one. Current evaluations often accept words or a realistic-looking image, so the predicted state is never checked against the true one. We introduce DynaPix (Dynamic Pixels), a benchmark that makes prediction checkable. Given a video clip that stops before a key event and a question about a later moment, a model must pick the true future image from close candidates or a large gallery. The scenes come from a physics simulator, so the correct image and its time are known exactly and the wrong options are deliberately similar. Models often succeed when a visible event marks the target moment, but are near chance when only elapsed time marks it. Gallery search is harder still, as the true image rarely ranks first. People handle the elapsed-time items well, so the difficulty lies with the models, not the questions. Training on scene accounts drawn from the simulator's true record, not a teacher's guess, repairs much of this but not the longer elapsed time case. DynaPix thus exposes a temporal-anchoring gap: models attach a prediction to an event far better than to time itself.

cs.CV↗
arXiv2026

CaIRec: Calibrated Modality Imputation for Incomplete Multimodal Recommendation

Real-world multimodal recommender systems often face incomplete modality observations, where items lack images, text, or other content features. Such incompleteness weakens item representations and degrades recommendation performance. Existing modality imputation methods estimate missing representations from available item content, but two challenges remain. First, they optimize the recovered representation itself without explicitly considering its relations with other modalities of the same item. The completed modalities may therefore form inconsistent cross-modal relations, causing Cross-modal Structural Distortion. Second, even structurally coherent recovered information may remain ineffective for personalized ranking. Recovered representations receive limited ranking-oriented guidance, while modality missingness disrupts the item neighborhoods required for preference propagation, resulting in a Preference Adaptation Gap. To address these challenges, we propose Calibrated Imputation for Incomplete Multimodal Recommendation (CaIRec), a two-stage framework. Structural Imputation Calibration (SIC) estimates missing-modality representations from shared information inferred from available modalities and calibrates their cross-modal organization through structural regularization and correspondence supervision from observed modality pairs. Preference-oriented Representation Calibration (PRC) performs recommendation-specific adaptation at both the representation and relation levels. It constructs pseudo-missing instances to align recovered representations with observed counterparts shaped by ranking supervision in the recommendation space. It further builds completion-aware item graphs by integrating completed content relations with collaborative evidence. Extensive experiments on three datasets under different modality-missing settings demonstrate the effectiveness and robustness of CaIRec.

cs.IR↗
arXiv2026

Learning from the Future: Privileged Self-Distillation for Sequential Recommendation

Sequential recommenders are commonly trained with one-hot next-item labels under a causal (prefix-only) objective aligned with inference. While deployment-compatible, this supervision offers little insight into relative preferences among non-target items. Yet logged interaction sequences contain an additional supervisory source: interactions following the target often reveal how user intent evolves, making the target easier to interpret. We treat these future interactions as training-only privileged information, available during learning but not at inference. This raises a natural question: can future interactions provide richer supervision while keeping training aligned with inference-time prediction? We propose Privileged Self-Distillation (PSD), a framework that separates learning-time information from inference-time information. PSD applies two attention masks to the same backbone: a future-aware view yields a privileged teacher distribution conditioned on past and future interactions, while a prefix-only view yields the student distribution used for deployment. Distilling the privileged distribution converts future interactions into training-only supervision rather than inference-time inputs. Since both views share a backbone, the teacher's advantage is purely informational, not architectural, removing the need for a separately pretrained teacher and letting its supervision adapt as the student evolves. PSD further uses an advantage-reachability gate to focus distillation on teacher signals likely supported by the observed prefix, along with a momentum-averaged teacher for stable targets. The framework is optimized end-to-end in a single stage, leaving the deployed model and inference cost unchanged. Experiments across public benchmarks and diverse backbones show consistent improvements.

cs.IR↗
arXiv2026

Eulerian Motion Guidance: Robust Image Animation via Bidirectional Geometric Consistency

Recent advancements in image animation have utilized diffusion models to breathe life into static images. However, existing controllable frameworks typically rely on Lagrangian motion guidance, where optical flow is estimated relative to the initial frame. This paper revisits the same optical-flow primitive through a more local supervision design: we use adjacent-frame Eulerian motion fields to guide generation, where the motion signal always describes a short temporal hop. This shift enables parallelized training and provides bounded-error supervision throughout the generation process. To mitigate the drift artifacts common in adjacent frame generation, we introduce a Bidirectional Geometric Consistency mechanism, which computes a forward-backward cycle check to mathematically identify and mask occluded regions, preventing the model from learning incorrect warping objectives. Extensive experiments demonstrate that our approach accelerates training, preserves temporal coherence, and reduces dynamic artifacts compared to reference-based baselines. The code, model, and data have been made available at https://nguyentthong.github.io/eulerian/

cs.CV↗
arXiv2026

De-attribute to Forget for LLM Unlearning

The rapid development of large language models (LLMs) has raised concerns on the use of inappropriate data for training, which has led to a growing interest in LLM unlearning. Many existing LLM unlearning approaches rely on optimizing prediction loss(es), such as maximizing the loss on the forget set, but often face critical issues like over-forgetting and poor model utility. To address them, this paper novelly frames the optimization objective for LLM unlearning as one of zeroing out data attribution instead. In particular, we propose the first LLM unlearning framework based on data attribution rewards called DareU that performs reinforcement learning to update the LLM by reducing the attribution score of its generated responses (i.e., de-attributing) to the forget data owners. Empirical evaluation using an LLM classifier as an efficient approximation of attribution shows that DareU outperforms existing baselines by achieving effective unlearning while balancing forget quality and model utility well.

cs.LG↗