arXiv subjects

Xiang Chen

Publications and source records attributed to Xiang Chen.

At least 19 recordsLinked to original sources

arXiv2026

Chain-of-Thought in Neural Code Generation: From and For Lightweight Language Models

Large Language Models (LLMs) have demonstrated remarkable potential in code generation. The integration of Chain of Thought (CoT) reasoning can further boost their performance. However, current CoT methods often require manual writing or LLMs with over 100 billion parameters to generate, impeding their applicability in resource-constrained scenarios. In this study, we investigate lightweight Language Models (lLMs), which are defined to have fewer than 10 billion parameters. Empirically, we find that most lLMs cannot generate high-quality CoTs when prompted by the few-shot method, but can take advantage of high-quality CoTs generated elsewhere to improve their performance in code generation. Based on these findings, we design a novel approach COTTON which can leverage lLMs to automatically generate CoTs for code generation. We synthesize new datasets and conduct extensive experiments on various benchmarks. The results show that the CoTs generated by COTTON outperform the baselines in terms of automated and human evaluation metrics. In particular, the CoTs generated by COTTON boost various lLMs to achieve higher performance gains than those generated by LLMs such as ChatGLM (130B), and are competitive with those generated by gpt-3.5-turbo (175B). Our study also showcases the potential of lLMs in software engineering applications.

cs.SE↗

arXiv2026

FedHQ: Hybrid Runtime Quantization for Federated Learning

Federated Learning (FL) must balance training efficiency and model accuracy across heterogeneous clients. Post-training quantization (PTQ) avoids the extra computation of quantization-aware training (QAT), but can incur greater accuracy loss. We propose FedHQ, a hybrid quantization framework that assigns PTQ or QAT according to clients' hardware and data characteristics. Hardware-based speed estimates and local data-distribution indicators guide coarse-grained global initialization, followed by fine-grained training-based adjustment of selected client strategies. Experiments on three image-classification datasets show that FedHQ achieves up to 2.47x training speedup over FedAQT and up to 11.15 percentage points higher accuracy than FedFQ.

cs.LG↗

arXiv2026

ActECC: Action Chunk Temporal Harnessing for Edge-Cloud Collaborative VLA Inference System

VLA models have emerged as the mainstream for embodied intelligence, which decouples reasoning and execution via action chunks. To enable real-time deployment of VLA models, existing studies investigate edge-cloud collaborative inference, which pose two challenges to the action chunk mechanism. (1) Edge-cloud collaboration complicates system latency components, hindering the determination of valid ranges for action chunks. (2) Latency fluctuations in cross-edge update links under edge-cloud scenarios make it difficult to schedule replanning requests. To address these, we analyze the key factors affecting action chunk usable ranges and replanning request timing, revealing phase dependence and edge-cloud latency constraints. Based on these insights, we propose ActECC, which enables Action Chunk Temporal Harnessing through kinematics-guided usable range assessment and delay-aware replanning scheduling. Experiments show that ActECC reduces per-action latency by up to 27.4% and cloud calls by up to 45.1%, while lowering average execution error compared with existing edge-cloud collaborative.

cs.DC↗

arXiv2026

When Entropy Is Not Enough: Reclaiming Lost Semantics in LLM Output Length Prediction

Efficient LLM serving is often bottlenecked by the need to pad sequences to a fixed maximum length, and this wastes compute and degrades throughput. Output length prediction enables length-aware scheduling and reduces overhead. Existing methods, including entropy-guided token pooling, rely on token-level entropy but overlook semantic differences between tokens, causing them to underweight important tokens and overemphasize less informative tokens. We introduce ESTP(Entropy-and-Semantic Token Pooling), a lightweight framework that combines entropy representations with attention-based semantic representations. By deriving both representations directly during prefill, ESTP captures uncertainty and semantic importance while incurring negligible additional inference latency and memory overhead compared with methods using external auxiliary models. On the ForeLen benchmark, ESTP outperforms baseline methods, achieves better prediction accuracy and lower prediction errors across most scenarios. When integrated with a length-aware scheduler in end-to-end system tests, it further improves overall throughput and reduces the padding ratio.

cs.AI↗

arXiv2026

VISAGENT: An Agent-Based End-to-End Voice Interaction System

Voice-based public services have evolved from manual switchboards to intelligent platforms to meet modern user needs. However, current systems remain constrained by rigid menu-driven interaction, fragmented vertical services, and limited extensibility. To address these issues, we present VISAGENT, an agent-based end-to-end voice interaction system for large-scale public services that integrates end-to-end speech interaction, hierarchical agent routing, a scalable voice-agent marketplace, and user memory support. The system replaces menu-driven workflows with natural speech and dynamically dispatches user requests to either a general conversational model or specialized domain agents via a two-level routing paradigm that achieves sub-second intent-to-agent selection over hundreds of agents. User memory informs preference-aware agent selection and supplies relevant preferences and context to selected agents, supporting personalized task execution and reducing the need for users to repeat previously provided information. A voice-agent registration mechanism converts task agents into conversational entities, enabling dynamic onboarding and ecosystem-level extensibility. We validate VISAGENT through a real-world deployment in China's 114 hotline across multiple service domains. Experimental results demonstrate low-latency full-duplex interaction, robust routing scalability, and competitive speech naturalness. More broadly, this work advocates a shift from isolated voice assistants toward agent-centric conversational infrastructures, providing a general blueprint for building extensible voice-agent systems in public services and beyond.

cs.CL↗

arXiv2026

Is Serving-Time Language-Model Inference Necessary for Recommendation? Evidence from Generative and Agentic Settings

Language models (LMs) are increasingly used in recommender systems to generate recommendations or coordinate recommendation tools. However, does their strong performance imply that serving-time LM inference is necessary? We challenge this seemingly reasonable but unverified assumption. To investigate this question, we introduce recovery-based mechanism auditing, which tests whether independent alternatives can achieve the accuracy of LM-based recommender systems without the audited inference mechanisms under controlled information and evaluation conditions. For generative recommendation, we propose LIME-Rec, which combines sequential, collaborative, and offline semantic information without autoregressive LM decoding. On three Amazon Reviews datasets (Beauty, Toys, and Sports), LIME-Rec achieves the highest reported mean in all 12 dataset-metric combinations, with up to a 15.2% relative improvement in Recall@10 over GRAM, an LM-based generative recommender. For agentic recommendation, we propose DART-Rec, which replaces LM-based tool control with deterministic fusion and fixed expert selection. On 1,000 Beauty users, given the same candidate items and expert scores, deterministic fusion achieves a 16.7% relative improvement in Recall@10 over a fine-tuned LM controller. With at most two tool calls, fixed expert selection matches the LM controllers' Hit@10 outcomes for every user in 17 of 18 comparisons. These findings demonstrate that strong recommendation performance does not necessarily require serving-time LM inference: under the evaluated task and information conditions, alternatives without the specified inference mechanisms can match or exceed the accuracy of their LM-based counterparts. To support reproducibility, code is available at https://github.com/Double-wk/LIME-Rec.

cs.IR↗

arXiv2026

Enhancing Knowledge Density via Hierarchical Context Pruning for Retrieval-Augmented Repository-Level Code Completion

Retrieval-Augmented Generation (RAG) has advanced repository-level code completion by retrieving external code snippets, API documentation, or type definitions to expand the model's contextual awareness. However, under the finite token budget of the context window, existing retrieval-augmented methods often saturate the budget with highly similar or even redundant code, which not only wastes tokens but also suppresses critical cross-file dependencies, preventing synergistic interaction between semantically similar reference snippets and cross-file dependency definitions. Therefore, further gains are limited by low knowledge density in the retrieved context rather than by model capacity. We propose SaraCoder, a retrieval-augmented framework that enhances knowledge density via hierarchical context pruning under a fixed context budget. A Hierarchical Feature Optimization module prunes an over-complete candidate pool in four stages. The freed tokens are then allocated to an External-Aware Identifier Disambiguator, which selectively injects only the most necessary cross-file dependency definitions. SaraCoder transforms context construction into a budget-aware optimization problem, balancing reference snippets and cross-file dependencies to build a context that is both knowledge-dense and semantically complete. Experiments on CrossCodeEval and RepoEval-Updated, across multiple backbone code LLMs, show that SaraCoder consistently outperforms strong RAG baselines such as GraphCoder and Repocoder in both code-level and identifier-level metrics, without increasing token usage, and yields synergistic gains when combined with other cross-file methods.

cs.SE↗

arXiv2026

MOCHA: Multi-Objective Chebyshev Annealing for Agent Skill Optimization

LLM agents organize behavior through skills -- structured natural-language specifications that govern how an agent reasons, retrieves, and responds. Unlike monolithic prompts, skills are multi-field artifacts with platform limits: descriptions are indexed for routing, instruction bodies are loaded into a shared context window, and every extra line costs the agent context it could spend elsewhere. Skill optimization is therefore inherently multi-objective: a skill should be accurate and economical at once. Existing prompt optimizers collapse these goals into a single score, and we find that this makes them stall: in most of their runs, 1000 rollouts yield zero progress over the seed skill. We introduce MOCHA (Multi-Objective CHebyshev Annealing), which selects skills to improve by Chebyshev scalarization and accepts improvements that expand the Pareto front, annealing from exploration to exploitation. Chebyshev scalarization scores a skill by its largest weighted shortfall from a perfect skill; with random weights, it can select any skill on the Pareto front for improvement, including trade-offs that an average would never favor. Across six diverse skills and two models, MOCHA escapes the seed in nearly every run, achieving 7.9% higher mean accuracy than the strongest baseline (up to 23.7% on DebugBench with GPT 5.5 and 14.9% on FEVER with Claude Haiku 4.5) while discovering Pareto fronts with the highest hypervolume and nearly twice as many Pareto-optimal skills.

cs.AI↗

arXiv2026

Teacher-Guided Tool Learning for Small Language Models via Bidirectional KL Constraints

External tools can extend the capabilities of small language models (SLMs), enabling their deployment in resource constrained environments. However, their limited capabilities make it difficult for SLMs to discover effective tool use behaviors through reinforcement learning alone, while direct teacher supervision suffers from teacher student behavioral distribution mismatch and may propagate erroneous preferences. To address these challenges, we propose Selective Teacher guided Policy Optimization (SeTPO), which coordinates student exploration with selective teacher guidance and persistent demonstration supervision. Specifically, SeTPO incorporates reverse KL derived token level teacher feedback into policy advantages on low reward trajectories, while auxiliary forward KL supervision preserves teacher demonstrated behaviors throughout training. Under an idealized bidirectional KL objective, we theoretically establish that the optimal policy achieves expected reward no lower than the teacher's while retaining a guaranteed fraction of the teacher's probability mass. Extensive experiments on BFCL v4 and API Bank demonstrate that SeTPO achieves superior overall performance over supervised fine tuning, reinforcement learning, and distillation baselines across all three student scales.

cs.LG↗

arXiv2026

StageBreaker: Shifting Video RL Post-Training Scheduling from Stages down to Data Dependencies

Reinforcement learning (RL) post-training has emerged as the key paradigm for improving autoregressive video models. Emerging vision-language reward models further strengthen post-training with accurate rewards, but their long chain-of-thought inference substantially raises the associated costs, while the pursuit of long videos prolongs policy training. Despite these rising costs, existing video RL systems still adopt coarse-grained stage-centric execution, which stalls policy training until all reward evaluation finishes, replays every trajectory twice due to a further barrier within policy training, and induces load imbalance across GPUs. To address the challenges, we propose StageBreaker, a fine-grained data-dependency-driven scheduling framework, which schedules the true dataflow of an RL step rather than its stages. Specifically, StageBreaker overlaps policy training with reward evaluation by exploiting reward-separable policy training, and merges the two trajectory replays into one by leveraging loss-independent back-propagation. It further balances GPU load by scheduling computation at the finer granularity. Our evaluation results show that StageBreaker achieves a speedup of up to 1.41$\times$ over stage-centric execution.

cs.DC↗

arXiv2026

The WZ pair and finite congruences

We construct a meromorphic Wilf--Zeilberger pair for the hypergeometric series for $3\ln 2$, completing the WZ proof left open by Guillera and Rogers. The same pair yields a one-parameter identity and, after a half-integer shift and differentiation, an inverse-binomial series for $ζ(3)$. We also study the finite truncations of the logarithmic series. For every prime $p\ge 5$, we prove that the lower truncation is congruent to $q_p(2)-1$ modulo $p$, while the upper truncation is congruent to $-\frac{7}{16}p^2B_{p-3}$ modulo $p^3$. The proofs combine the WZ method with terminating hypergeometric identities, the Pfaff--Saalschütz identity, and classical congruences for harmonic sums.

math.NT↗

arXiv2026

FireNav: Decision-Oriented Reconstruction Evidence Routing for Vision-Language Navigation in Indoor Fire Environments

In real-world indoor fire environments, visual degradation severely impairs instruction grounding, waypoint prediction, and long-horizon exploration in vision-language navigation (VLN). Although image restoration offers a natural means to mitigate such visual degradation, existing methods primarily optimize reconstruction fidelity, which does not necessarily translate into better navigation decisions and may even corrupt task-critical cues when applied indiscriminately. In this paper, we present FireNav, a decision-oriented reconstruction evidence routing framework that aligns visual restoration with navigation utility in VLN. To advance this task, we first contribute FireVLN-Bench, a paired indoor fire navigation benchmark with clean references preserving task semantics, safety supervision, and matched settings for continuous navigation and robot execution with simulated dynamics. Our FireNav retains native visual tokens and treats latent reconstruction features as auxiliary evidence, where a lightweight router leverages visual features, task context, and prior execution states to determine whether such evidence should be admitted and how strongly it should contribute to the visual tokens. To learn when reconstruction is beneficial, we further introduce decision utility calibration, which compares action prediction losses with and without candidate evidence under the same state, thereby supervising evidence selection according to its contribution to waypoint, heading, and arrival prediction. Experiments demonstrate that FireNav consistently outperforms state-of-the-art baselines in both navigation success and path efficiency across evaluation settings.

cs.CV↗

arXiv2026

What Do Sparse Autoencoder Feature Discovery Scores Identify? From Activations to Interventions

Sparse autoencoder (SAE) features are typically discovered from how their activations co-vary with behaviour, yet they are often used through interventions such as steering or ablation. We take intervention attribution, the first-order effect of a specified intervention on the model output, as our estimand. For a broad class of response functions, we show that observational feature-discovery evidence generally does not identify this attribution, and derive an exact gradient-based decomposition of the gap between linear-probe predictions and intervention attribution. Across four model-SAE pairs, median probe-to-attribution magnitude ratios range from tens to hundreds, while attributions closely track small-step steering. For single-latent ablations with nonzero effects, gradient predictions match the realized sign in 91-97% of cases, compared with 17-35% for probe-implied changes. Attribution-selected sets also produce larger absolute mean ablation effects on held-out prompts than sets selected by correlation, rank tests or probe coefficients. Together, these results establish intervention attribution as a principled, gradient-estimable target for selecting SAE features for intervention.

cs.LG↗

arXiv2026

Query-Adaptive Neuron Steering for LLMs

Effectively eliciting the capabilities of large language models (LLMs) at inference time remains an important challenge. Existing studies address this challenge through context engineering, which shapes user queries, or fixed steering, which directly intervenes in model computation. However, predefined contexts and fixed intervention strategies may not adequately accommodate the diverse knowledge and reasoning requirements of individual queries. This raises a natural question: Can internal steering in LLMs be made query-adaptive? In this work, we investigate whether query-induced internal activations can guide adaptive steering in LLMs. Our pilot studies reveal subject- and layer-dependent neuron activation patterns and show that amplifying subject-relevant neurons can improve model performance. Based on these findings, we propose Q-NeuS, a query-adaptive neuron steering framework that dynamically determines which neurons to modulate and by how much for each input. Specifically, Q-NeuS constructs a compact subject-guided candidate neuron space and employs a lightweight Query-Adaptive Gate to generate neuron-wise modulation coefficients. To learn effective intervention strategies, we introduce Neu-GRPO, which adapts group-relative optimization to train the Query-Adaptive Gate using the relative performance of multiple neuron intervention configurations. The base LLM remains frozen throughout training and inference, and no task or subject labels are required at inference time. Extensive experiments across multiple LLMs and benchmarks demonstrate that Q-NeuS consistently improves model performance and exhibits broad applicability across model scales and strong cross-benchmark transferability.

cs.LG↗

arXiv2026

Decoupling Knowledge Forgetting and Refusal Learning in MLLM Unlearning

Current evaluations of multimodal unlearning typically focus on whether a model stops outputting target information. This surface-level criterion, however, masks two critical failure modes. First, knowledge suppression techniques often induce confabulation, leading the model to hallucinate facts about the unlearned subject. Second, refusal training merely alters observable behavior without erasing the underlying knowledge; such models might decline open queries but still identify correct answers under multiple-choice probing. To overcome these limitations, we propose Forget-Aware Self-Distillation (FASD). This method is designed to achieve honest ignorance, a state where the model genuinely loses the target knowledge and learns to acknowledge its absence. FASD separates these goals into two complementary channels. The behavior channel distills appropriate refusals from an ignorance-prompted copy of the model itself. Crucially, target tokens are masked from the teacher distribution to avoid accidentally reteaching the forgotten concepts. Simultaneously, the knowledge channel directly suppresses ground-truth answer spans independently of the model's generated responses. Experiments demonstrate that FASD successfully unlearns target knowledge, prevents information leakage in open-ended tasks, and preserves performance on retained data. The resulting model not only forgets the specified information but accurately recognizes the boundaries of its own knowledge. Code and data will be released upon publication.

cs.AI↗

arXiv2026

Beyond Visual Enhancement: Adaptive Multi-Context Steering to Mitigate LVLM Hallucinations

Hallucination remains a significant challenge in Large Vision-Language Models (LVLMs). Existing training-free methods generally mitigate hallucinations through contrastive decoding or visual enhancement, often increasing the relative influence of visual evidence during generation. This raises a fundamental question: Can LVLMs dynamically regulate the contributions of different context sources to suppress hallucinations? In this work, we investigate and quantify how LVLMs coordinate multiple context sources during decoding and examine how this intrinsic behavior can guide hallucination mitigation. We find that LVLMs exhibit an intrinsic vision-attending tendency that can guide adaptive visual steering, while textual contexts can also contribute to hallucination mitigation. Motivated by these findings, we propose AIMS (Adaptive Information Multi-source Steering), a lightweight training-free framework that adaptively coordinates visual, prefilled textual, and generated contexts during decoding. Specifically, AIMS constructs compact prototypes for the three context domains and estimates their affinities with the current query to determine head-wise steering weights. The resulting multi-source steering direction is applied to the query representation, enabling adaptive context integration without additional model training or auxiliary forward passes. Extensive experiments across multiple LVLMs and decoding strategies demonstrate that AIMS effectively mitigates object hallucination while maintaining competitive general-purpose multimodal capabilities.

cs.CV↗

arXiv2026

Search for Visible Dark Photon Decays at the Future SHINE Facility with the DarkSHINE Experiment

We study the sensitivity of the proposed DarkSHINE experiment to displaced dark photon decays, $A'\to e^+e^-$, using an 8~GeV electron beam incident on a tungsten target. We consider $2m_e<m_{A'}<2m_μ$ and assume a unit branching fraction to electron--positron pairs. Signal events generated at tree level with \textsc{CalcHEP} are propagated through a detailed \textsc{Geant4} detector simulation. A close tracker, graph-neural-network-based track reconstruction, and displaced vertex selections suppress prompt pair-production and photon-conversion backgrounds, while calorimeter and invariant-mass requirements render hadronic backgrounds negligible. Extrapolation of the residual prompt-background distribution yields 0.3 expected events for $9\times10^{14}$ electrons on target. The median expected 90\% confidence-level exclusion covers masses of approximately 30--70~MeV and kinetic mixing parameters from approximately $5\times10^{-5}$ to $2\times10^{-4}$. This visible decay search complements DarkSHINE searches for invisible dark photon decays.

hep-ex↗

arXiv2026

Regulating oxygen content and superconductivity in La$_3$Ni$_2$O$_{7+δ}$

The synthesis of high-quality Ruddlesden-Popper (RP) nickelates remains challenging due to variations in oxygen content and the prevalence of intergrown RP phases. Precisely controlling the stoichiometry and characterizing the resulting physical properties are essential for understanding the mechanism of high-$T_c$ superconductivity in these materials. In this work, we synthesize a series of La$_3$Ni$_2$O$_{7+δ}$ samples with systematically controlled oxygen content and perform comprehensive structural and compositional analyses. Precise oxygen tuning enables us to tailor the microstructure, yielding a pure bilayer phase, a mixture of bilayer and hybrid single-layer-bilayer phases, and a predominantly bilayer phase containing trilayer intergrowths. High-pressure transport measurements reveal distinct superconducting transitions with contrasting $T_c$ values, corresponding to the bilayer phase, the hybrid phase, and trilayer inclusions. Notably, we find that oxygen content not only governs the phase purity$-$i.e., the presence of intergrowth phases$-$but also directly modulates the upper critical field ($H_{c2}$) of the bilayer superconductivity. By establishing a phase diagram of $T_c$ and $H_{c2}$ as functions of oxygen content in La$_3$Ni$_2$O$_{7+δ}$, this work advances synthetic control and provides new insights into the superconducting mechanism of RP nickelates.

cond-mat.supr-con↗