arXiv subjects

Anh Tuan Luu

Publications and source records attributed to Anh Tuan Luu.

At least 19 recordsLinked to original sources

arXiv2026

CodeArena: A Collective Evaluation Platform for LLM Code Generation

Large Language Models (LLMs) have reshaped code generation by synergizing their exceptional comprehension of natural language and programming syntax, thereby substantially boosting developer productivity. These advancements have prompted numerous efforts to quantitatively evaluate their coding capabilities. However, persistent challenges, such as benchmark leakage, data dissipation, and limited system accessibility, continue to impede a timely and accurate assessment. To address these limitations, we introduce CodeArena, an online evaluation framework tailored for LLM code generation. The key innovation is a collective evaluation mechanism, which dynamically recalibrates individual model scores based on the holistic performance of all participating models, mitigating score biases caused by widespread benchmark leakage. In addition, CodeArena ensures open access to all submitted solutions and test cases and provides automation-friendly APIs to streamline the code evaluation workflow. Our main contributions are: (1) a collective evaluation system for unbiased assessment, (2) a public repository of solutions and test cases, and (3) automation-ready APIs for seamless integration.

cs.SE↗

arXiv2026

Diagnosing the Reference Gap: What Visual Scaffolds Can and Cannot Fix in Multimodal Reasoning

Multimodal large language models can recognize visual content yet struggle to reason reliably over it across multiple steps. In counting, a model may see all objects but lose track of which ones it has counted. We argue that such failures, commonly attributed to perception, reveal a reference gap: the failure to bind language to the relevant visual entities, regions, or locations. Motivated by the theory of visual routines, we test whether external references such as numbering can narrow this gap. We introduce ReGap-Bench, a paired benchmark of five visual reasoning tasks in which the scene, question, and answer are fixed and only the reference varies. Results show that task-matched references improve accuracy by up to 25\%, while mismatched references provide little benefit or even hurt performance. These findings identify the reference gap as a bottleneck distinct from visual perception and show that constructing task-appropriate visual references can serve as a training-free visual skill for improving multimodal reasoning.

cs.CV↗

arXiv2026

What Hallucinations Have We Measured? Semantic Illusion, Confabulation, and Expressed Uncertainty

Hallucination remains one of the most critical challenges in deploying large language models (LLMs) reliably and safely. Yet the term is used inconsistently across the research community. We argue for a strict definition of hallucinations in LLMs. First, hallucinations should be confident incorrectness, kept separate from expressed uncertainty (UNK)1. UNK reveals that the model may be wrong, whereas a hallucination does not reveal it and is therefore more dangerous in practice. Conflating the two obscures their distinct behaviors and makes them hard to study. Second, hallucinations should be split by a simple re-elicitation test: does any semantically equivalent prompt recover the correct response? This test probes whether the relevant knowledge2 is accessible. If none does, the knowledge is likely absent or inaccessible, and the error type is a confabulation (CF) that likely requires external knowledge or retraining; if some does, the knowledge is accessible from the model but applied inconsistently, and the error type is a semantic illusion (SI) that simple prompt or decoding changes can mitigate3. Re-evaluating 14 recent hallucination methods under this taxonomy yields three findings. (1) Detection methods flag UNK more often than hallucinated responses (i.e., SI and CF). (2) Mitigation methods are far more effective for SI than for CF. (3) Latent signals are more informative than output-level signals for CF. An audit of recent hallucination papers shows that most conflate these categories. We recommend reporting CF, SI, and UNK separately, and introduce a practical labeling protocol that needs only a modest number of semantically equivalent prompts.

cs.CL↗

arXiv2026

Evolve on Graph: Self-Evolving Knowledge Graph Reasoning without Question Annotations

Knowledge graphs (KGs) provide reliable external knowledge for multi-hop factual reasoning with large language models (LLMs), yet most KGs in real-world domains such as finance and industry lack question--answer (QA) annotations. Without such annotations, existing methods struggle to improve LLM graph reasoning: training-free agents cannot improve their exploration through interaction; reinforcement learning (RL) agents depend on QA data annotated by humans or synthesized by closed-source models; and training data is typically built offline, so its topology mix is fixed and cannot follow the agent's ability. We propose Evolve on Graph (EoG), a framework that lets an LLM self-evolve its graph reasoning without any QA annotations. Through Graph Self-Play, a single LLM alternates between a Proposer that poses questions and a Solver that answers them. To make questions verifiable, Symbolically Verifiable Topology Synthesis (SVTS) samples reasoning topologies on the KG and executes the corresponding first-order logic queries, yielding topology skeletons with correct and complete answer sets; guided by a skeleton, the Proposer explores the graph to pose a multi-hop question. To let task topologies follow the Solver, a Boundary-Aware Graph Curriculum rewards the Proposer by the Solver's score variance, keeping questions at the Solver's capability boundary so that complex topologies enter training as the Solver improves. On six benchmarks over Freebase, Wikidata, and an industrial KG, EoG consistently outperforms prompting-, retrieval-, and agent-based methods, showing that LLM graph reasoning can improve through self-play without QA annotations. Our code is available at https://github.com/Szy5/EoG

cs.AI↗

arXiv2026

Towards Reliable Truth-Aligned Uncertainty Estimation in Large Language Models

Uncertainty estimation (UE) aims to quantify uncertainty in large language model (LLM) outputs to flag potential hallucinations and support reliable deployment. However, UE metrics often exhibit unstable performance across models and datasets, limiting their practical utility. We formalise this phenomenon as proxy failure, arising because UE metrics are derived from model behaviour rather than being explicitly grounded in factual correctness. We show that when mutual information between a UE score and correctness is low, the score's discriminability must be close to chance. To address this, we propose Truth AnChoring (TAC), a lightweight post-hoc calibration method that maps raw UE scores to truth-aligned correctness probabilities. Even with noisy and few-shot supervision, TAC continues to improve calibration, providing a practical calibration protocol. Our findings highlight the limitations of treating heuristic UE metrics as direct indicators of uncertainty about factual correctness, and position our TAC as a principled step toward more reliable uncertainty estimation for LLMs. The code repository is available at https://github.com/ponhvoan/TruthAnchor/.

cs.AI↗

arXiv2026

Truth in Contrast: Calibrated Factual Evidence from Language Model Likelihoods

Large Language Models (LLMs) encode substantial factual knowledge. Yet, estimating confidence in factual claims reliably remains challenging. We study likelihood-based factual confidence from the complementary perspectives of discrimination and calibration across multilingual factual statements. Specifically, we instantiate contrastive generative likelihoods as Contrastive Factual Evidence (CFE), which compares the likelihood of the same claim under competing factual and non-factual conditions, and derive its probabilistic counterpart, the Contrastive Factual Posterior (CFP). We show analytically that CFP calibration depends on the differential error between the two surrogate conditionals, allowing errors shared across them to cancel and yield tighter calibration bounds. Empirically, CFP substantially improves calibration while maintaining factual discrimination comparable to its strongest competitor. Nonetheless, discrimination is uniformly weak across methods in lower-resource languages, which simultaneously undermines the utility of the measured calibration. To this end, we interpret a likelihood geometry, within which an evidence-bearing direction is induced, along with an orthogonal evidence-invariant direction. In our investigation, we selectively align target-language claims with stronger English evidence only along the factual-evidence direction, improving discrimination and open-ended factual generation without target-language labels.

cs.CL↗

arXiv2026

From Signals to Transfer: A Factorised Study of Probe-Based Uncertainty Estimation in Large Language Models

Probe-based uncertainty estimation (UE) has emerged as a prominent approach to detect hallucinations in Large Language Models (LLMs) by learning uncertainty from internal model signals. Yet, recent methods vary simultaneously across feature design, training data construction, and evaluation setting, obscuring what actually drives performance. To address this issue, we propose a factorised study of probe-based UE under matched conditions. Our results show that raw hidden states and attention features are difficult to outperform in-domain. However, under distribution shift, structured and compressed features are more robust, suggesting that in-domain performance alone is insufficient to measure progress. Furthermore, prompting and label construction significantly affect probe behaviour. Building on these empirical design principles, we construct benchmark-pretrained probes that retain useful discriminative signal on open-ended factual generation. Their competitive performance relative to limited-label target setting probes and sampling-based estimators suggests that they can provide a practical starting point for subsequent target-domain adaptation. More broadly, our work encourages deployment-oriented evaluation of probe-based uncertainty estimators.

cs.CL↗

arXiv2026

PowerAtlas: Feasibility-Aware Language Models for Electricity-Computing Co-Scheduling

Electricity-computing co-scheduling (ECCS) decides where and when computing tasks run together with how generators are dispatched, because task placement changes nodal demand while power availability determines whether tasks can be served. Prior work addresses such coupled problems with optimization or learned controllers, and large language models (LLMs) are increasingly used to generate structured decisions for scheduling and power systems. Solver runtimes vary across instances, and LLM outputs that parse correctly can still violate grid and service constraints. We formalize ECCS as a structured decision task and release ECBench, 2,000 instances with Gurobi-optimal reference schedules and executable checks for grid limits, task service, cost, and latency. We propose PowerAtlas, which trains an LLM with supervised initialization and Feasibility-Aware GRPO on deterministic scorer feedback, and generates the joint schedule in a single response without solver calls or retrieval. On 10-40 paired instances per backbone, selected PowerAtlas checkpoints lower violations by 89-98% and penalized cost by up to 26x relative to base models, with residual supply deficits. Code and data are available at https://github.com/JAVA-Jiang/PowerAtlas.

cs.LG↗

arXiv2026

Activation Steering Induces Emergent Misalignment: Steering Vector Construction and Comprehensive Evaluation

Activation steering (AS) has emerged as a popular inference-time technique for modulating the behavior of large language models (LLMs). AS modulates model behavior in a flexible and lightweight manner by injecting task-specific steering vectors (SVs) into intermediate activations. Meanwhile, recent work has identified emergent misalignment (EM) as an emerging safety concern, whereby finetuning on unsafe examples from a narrow task unexpectedly induces broadly unsafe behavior in unrelated domains. With the increasing popularity of AS, it is pressing yet under-explored to thoroughly investigate whether AS can induce EM. In this paper, we conduct a comprehensive study of activation-steering-induced emergent misalignment. Specifically, (1) we identify a steering vector construction to confirm that SVs derived from a narrow task can indeed induce misalignment across broad unrelated domains. Qualitative measurement further reveals that AS-induced EM may pose more severe safety risks than finetuning-induced EM, i.e., AS elicits more actionable harmful responses with greater semantic coherence than those generated by finetuned models. (2) We characterize the properties of AS-induced EM by analyzing key steering-specific factors, including steering magnitude, the low-rank structure of the steering subspace, and the number of fine-tuning epochs used during steering-vector construction. (3) We evaluate the robustness and sensitivity of AS-induced EM across diverse model families, model scales, target tasks, and intervention layers. Our findings reveal activation steering as a significant yet underexamined source of emergent misalignment and provide an activation-space perspective on emergent misalignment and its safety risks.

cs.LG↗

arXiv2026

Reliable Memory from Unstable Growth: Curating Self-Written Agent Playbooks with Randomized Experiments

Persistent textual memory lets language-model agents reuse lessons from past tasks to improve on future multi-step tasks without retraining. Systems such as ACE and Dynamic Cheatsheet keep it as a playbook: lessons the agent writes after each task and reads in its prompt. A key challenge is to decide which lessons improve later tasks. Current systems leave the decision to the agent itself, which makes performance unstable: the same procedure can write a playbook that helps or one that falls up to 69.6 points below no playbook. These findings motivate valuing lessons by their measured effect on task success rather than by the agent's judgment. We propose Randomized Block Curation (RBC), which measures this effect with a randomized experiment on practice tasks. It groups related lessons into blocks large enough to move success measurably and, on each practice task, includes or leaves out every block at random. Random inclusion makes tasks with and without a block comparable, so the gap in their success estimates the block's effect. RBC keeps the blocks that help and, since the same procedure can write a helpful or a harmful playbook, grows several and serves whichever curated, whole or no playbook scores best on fresh practice episodes. Across two memory systems, three models and three benchmarks, RBC raises average success to 66.9, against 55.5 with the whole playbook, 54.1 with no playbook and 53.8 when the agent's own judgment picks the lessons to keep.

cs.CL↗

arXiv2026

Copying Is Not Grounding: Training Faithful Long-Form RAG with Authored-Sentence Credit

In search engines and assistants, long-form RAG answers can mislead readers with claims their sources do not support. Faithfulness rewards, the share of supported sentences, train models toward fewer such claims. We show that these rewards are hacked by copying. A sentence copied from the passages is supported almost by construction, so trained models learn to copy rather than ground what they write. Common defenses only move the hack: a KL or copy penalty leaves copying in place or trades it for shorter, emptier answers and refusals. GRPO, the standard RL algorithm, makes it worse by giving every sentence its answer's advantage, reinforcing copied and grounded sentences alike. We propose Authored-Sentence Credit (ASC) , which fixes both by moving GRPO's reward and advantage from the answer to the sentence level. The reward credits only sentences that are authored rather than copied, say more than the question, and are supported by the passages. The advantage compares each sentence with every sentence sampled for the question, so one that earns no credit ranks last and is never reinforced. Across four models and two in-domain, three held-out corpora, only ASC lowers the error rate of authored sentences and writes more supported ones in every setting, by 38% and 46% at the median under held-out evaluators, giving readers more grounded information. It takes none of these shortcuts, and two LLM judges comparing whole answers prefer no baseline to the base model but rate ASC's answers on par with it. We conclude that a faithfulness reward should credit what a model writes, not what it copies.

cs.CL↗

arXiv2026

CataOPD: Catalytic On-Policy Distillation for Large Language Model Reasoning

Reinforcement learning (RL) and on-policy distillation (OPD) are two representative paradigms for improving large language model reasoning. However, when no correct trajectory is sampled, RL lacks a positive correctness signal, while OPD remains constrained by the reasoning trajectories reachable under the student's on-policy distribution. Therefore, we propose CataOPD, where the teacher acts as a catalyst rather than a target, expanding reachability while internalizing verified student-produced trajectories into a catalyst-free policy. Self-Rescue Routing uses empirically all-failed groups as routing signals rather than teacher-intervention triggers, first seeking correct trajectories through additional on-policy self-sampling. For problems unresolved after self-rescue, Catalytic-Guided Self-Resolution uses catalytic guidance to elicit a verified student-produced trajectory in the guided student distribution. Barrier-Weighted Internalization weights tokens by guided-to-unguided log-probability gaps, focusing updates on decisive tokens difficult without guidance. Experimental results show that CataOPD outperforms current baselines, extends independent student reasoning to still-unrecovered problems, and improves out-of-distribution generalization under catalyst-free inference. Our project is available at https://github.com/QwenQKing/CataOPD.

cs.LG↗

arXiv2026

SCAD: Structured Credit Assignment and Distillation for Long-Horizon Agents

Training long-horizon agents to solve complex tasks requires effective supervision over extended interaction sequences. However, sparse terminal rewards obscure intermediate contributions, while on-policy distillation can lose informative teacher guidance as student-generated histories grow. To address this problem, we introduce SCAD, which organizes interactions into planning and bounded subtask execution, distills execution in local contexts, and refines planning credit through cross-rollout subtask prefix trees, with planning receiving full terminal credit and execution receiving positive terminal credit and teacher guidance. Across all evaluated benchmarks, SCAD improves macro-average accuracy over the strongest training baseline by 4.48 percentage points for text tasks and 4.19 points for multimodal tasks. SCAD effectively combines outcome-based credit assignment with teacher-guided distillation to improve planning and execution in long-horizon agents.

cs.LG↗

arXiv2026

When In-Distribution Gains Fail: Evaluating Weak-to-Strong Reward Models under Preference Shift

Weak-to-strong (W2S) generalization is a promising framework for scalable oversight, yet existing evaluations often test students under matched train-test distributions. Therefore, we study W2S preference learning under zero-shot distribution shift and find that strong students trained on weak preference labels can appear successful in-distribution while failing to transfer across preference datasets. We provide evidence for a representational failure mode in which weak-supervised fine-tuning can pull the strong model toward source-domain features instead of maintaining broadly transferable preference representations. To mitigate this, we propose Representation Anchoring (Anchor), a simple yet effective regularizer that constrains excessive drift from the pretrained strong model's representation space during fine-tuning, while still allowing task-relevant adaptation. Across preference domains, datasets, and model families, Anchor consistently improves out-of-distribution transfer while maintaining competitive in-distribution performance. Together, our evaluation protocol, transfer-aware metrics, and method expose hidden brittleness in current W2S reward modeling and provide a practical path toward more robust preference transfer.

cs.CL↗

arXiv2026

Practical Secrets Extraction against Black-box LLMs

Large language models (LLMs) increasingly power autonomous coding agents such as Codex and Claude Code, yet their training corpora may contain confidential credentials exposed in public repositories or collected from private development artifacts, creating risks of memorization and subsequent leakage. Existing extraction audits, however, largely assume access to model weights or token probabilities. In this work, we present a black-box secret extraction framework for commercial, API-based LLMs under output-only access. It comprises (i) \emph{Cross-Validated Secret Knowledge Distillation}, which uses semantics-preserving prompt variants, response cross-validation, and provider-specific format filtering to distill secret-relevant behavior into a local white-box proxy; and (ii) \emph{Proxy-Guided Secret Extraction and Candidate Filtering}, which combines truncated top-$p$ sampling with local token entropy, $N$-gram frequency profiling, and provider-specific structural priors. On controlled API-key benchmarks, our framework improves recovery effectiveness and real-key rates over representative baselines while reducing extraction latency. A responsible real-world evaluation further recovers masked provider-specific credentials from three independently deployed black-box LLM systems spanning OpenAI and Claude Code, showing that memorized secrets can be exposed under output-only access.

cs.CR↗

arXiv2026

Diachronic Hypergraphs for Orchestrated Multi-Agent Multimodal Memory Curation

Multi-agent systems solve tasks through collaboration, tool use, multimodal reasoning, and orchestration, but each agent operates within a knowledge boundary defined by its observations, context, and resources. Memory must preserve and transfer evidence, role specific context, decisions, procedures, and experience across interactions, not only outcomes. Vector and graph memories flatten these structures into embeddings or dyadic traces, obscuring events involving agents, tools, documents, errors, and evidence. This limits knowledge sharing, tracing, reuse, revision, and orchestration. We present MAGE, a hypergraph based multimodal database designed as a memory engine for MAS. MAGE stores agents, messages, tools, errors, procedures, documents, entities, decisions, and evidence in a heterogeneous temporal hypergraph, preserving high order collaborative events as reusable memory. It supports decision driven updates, role aware retrieval, validation, lifecycle management, and budget bounded context packing. By delivering knowledge to agents and orchestrators, MAGE expands their knowledge boundaries without modifying the models. Experiments show MAGE outperforms on various memory baselines.

cs.DB↗

arXiv2026

TIEM: Temporal Integration of Hypergraph Evidence and Skill Memory for Event-Driven Financial Forecasting

Event-driven catalyst-outcome forecasting increasingly uses retrieval- and memory-augmented large language model agents for prediction. However, training-data contamination and temporal leakage can create an Evidence Chasm between reported accuracy and true predictive ability. We propose TIEM, a timestamp-gated framework with three coordinated components: an Event-Evidence Hypergraph (EEH) for timestamp-filtered multi-tier retrieval; a Case-based Skill Memory (CSM) for source-tagged temporal skills; and Heterogeneous Evidence-Experience Fusion Reasoning (HEFR) for evidence-experience fusion and prediction. We also introduce FinPURE, a recent-period A-share holdout benchmark, and use a Name-Date Probe to assess per-model name-date sensitivity rather than assuming training cutoffs. Results on five financial forecasting benchmarks show TIEM outperforms current baselines. Our project is available at https://github.com/QwenQKing/Fin_TIEM.

cs.CE↗

arXiv2026

NS-VLA: Towards Neuro-Symbolic Vision-Language-Action Models

Vision-Language-Action (VLA) models are formulated to ground instructions in visual context and generate action sequences for robotic manipulation. Despite recent progress, VLA models still face structure-blind backbones, backbone-bound generalization, and flat single-objective optimization. To address these challenges, we propose a novel Neuro-Symbolic Vision-Language-Action (NS-VLA) framework. It introduces a Neuro-Symbolic Encoder for plan-constrained primitive inference, a Neuro-Symbolic Solver that conditions a backbone-agnostic policy on the active primitive, and Hierarchical Joint Policy Optimization with reward-granularity matching. Experiments on robotic manipulation benchmarks demonstrate that NS-VLA outperforms previous methods in both one-shot training and data-perturbed settings, while simultaneously exhibiting superior zero-shot generalizability and expanded exploration space. Our code is publicly available.

cs.RO↗