Search arXiv⌕ Search

arXiv subjects

Junjie Chen

Publications and source records attributed to Junjie Chen.

At least 37 records · Page 2Linked to original sources
arXiv2026

Multi-Source Retrieval and Reasoning for Legal Sentencing Prediction

Legal judgment prediction (LJP) aims to predict judicial outcomes from case facts and typically includes law article, charge, and sentencing prediction. While recent methods perform well on the first two subtasks, legal sentencing prediction (LSP) remains difficult due to its need for fine-grained objective knowledge and flexible subjective reasoning. To address these limitations, we propose $MSR^2$, a framework that integrates multi-source retrieval and reasoning in LLMs with reinforcement learning. $MSR^2$ enables LLMs to perform multi-source retrieval based on reasoning needs and applies a process-level reward to guide intermediate subjective reasoning steps. Experiments on two real-world datasets show that $MSR^2$ improves both accuracy and interpretability in LSP, providing a promising step toward practical legal AI. Our code is available at https://github.com/cjj826/MSR2.

cs.IR↗
arXiv2026

Benchmarking LLM-as-a-Judge for Long-Form Output Evaluation

As large language models (LLMs) are increasingly used for long-form generation, reliably evaluating long-form outputs has become a critical challenge. LLM-as-a-judge offers a scalable alternative to human evaluation, yet its reliability in long-form output evaluation remains underexamined: existing meta-evaluation benchmarks focus mainly on short-form outputs. Compared with short-form evaluation, long-form evaluation is not merely a matter of output length; it often requires judges to make more complex document-level assessments of overall organization, task-relevant coverage and depth, cross-section consistency, and scenario-specific quality criteria. In this work, we introduce LongJudgeBench, a comprehensive benchmark for evaluating LLM judges on long-form outputs across diverse real-world scenarios and judging protocols. We systematically evaluate a broad range of LLM judges, covering multiple base models and judging settings. Our results reveal a substantial reliability gap: current LLM judges remain unstable across scenarios, and rubrics or references are helpful but not always sufficient. We hope LongJudgeBench will support future research on more robust, context-aware, and human-aligned LLM-as-a-judge methods. Our code is available at https://github.com/cjj826/LongJudgeBench.

cs.CL↗
arXiv2026

FireRedAudio: A General-Purpose Audio Language Model with Decoupled Continuous Representations for Understanding and Generation

A unified audio model must recognize and understand linguistic, paralinguistic, and environmental information while supporting speech synthesis and editing. A key challenge is representation: understanding favors compact features suited to long-context modeling, whereas speech generation requires reconstructible features that preserve fine-grained acoustic detail. We introduce FireRedAudio, a general-purpose audio language model with a shared 9B-parameter LLM. To the best of our knowledge, it is the first publicly disclosed unified audio-language model to provide separate continuous input representations for understanding and generation within a single trainable autoregressive LLM. Audio to be recognized or analyzed is processed by a dedicated Audio Encoder, while speech inputs for generation use a RedAE-based pathway. The LLM directly generates text or conditions a flow-matching DiT to produce continuous acoustic latents. Through progressive multitask training, FireRedAudio supports ASR and audio understanding, with the latter extending to recordings of up to one hour, as well as zero-shot TTS, Instruct TTS, and semantic and acoustic speech editing. Its structured organization of long-form audio achieves second-level timestamp accuracy. Across comprehensive evaluations, FireRedAudio achieves competitive or leading performance in audio understanding and multilingual ASR, strong content accuracy and speaker preservation in zero-shot TTS, leading instruction following in Instruct TTS, and substantial improvements over Ming-UniAudio-Edit in both semantic and acoustic speech editing. These results demonstrate the viability of decoupled continuous input representations for unifying audio understanding and continuous-latent speech generation in a model of moderate scale. Our code is available at https://github.com/FireRedTeam/FireRedAudio.

cs.CL↗
arXiv2026

Self-supervised Learning Matters: A Simple Ensemble Solution for Micro-Gesture Recognition

In this paper, we present XInsight Lab's solution to the micro-gesture classification track of the 4th MiGA Challenge at IJCAI 2026, in which our solution ranked first and achieved a new state-of-the-art result. We propose a multimodal ensemble framework that integrates a self-supervised RGB-based model with supervised multi-stream models from previous solutions. The self-supervised RGB model is pretrained on 120K unlabeled clips via masked video modeling and then fine-tuned on iMiGUE. This simple yet effective RGB baseline achieves 69.224% top-1 accuracy on the iMiGUE test set, demonstrating the benefit of learning transferable representations from unlabeled in-domain videos. By incorporating this model as a complementary branch, the final ensemble reaches 74.419% top-1 accuracy, surpassing the previous state of the art by 1.206 percentage points. Experimental results on iMiGUE, including ablation studies on the ensemble strategy, validate the effectiveness of self-supervised RGB representation learning for micro-gesture recognition.

cs.CV↗
arXiv2026

Dynamic Gated Cross-Modal Fusion with Sarcastic-aware Contrastive Regularization for Multimodal Sarcasm Detection

Multimodal sarcasm detection aims to identify sarcastic intent from multimodal content, where inconsistencies between literal meaning and contextual cues often signal irony. This task has attracted increasing research attention. However, accurate detection remains challenging due to instance-dependent modality contributions and misleading semantic consistency, where surface-level alignment masks underlying contradictory intent. Existing methods often rely on fixed fusion strategies and treat sarcasm as generic cross-modal mismatch, limiting their ability to capture subtle sarcasm cues and instance-specific modality interactions. To address these challenges, we propose a novel MSD framework that integrates Dynamic Gated Cross-Modal Fusion with Sarcastic-aware Contrastive Regularization (SaCR). Specifically, a bidirectional gated interaction module performs cross-modal feature filtering and adaptively calibrates textual and visual contributions at the instance level. A dynamic fusion gate further balances modality importance to generate more robust multimodal representations. Furthermore, SaCR is introduced as a label-aware contrastive regularization objective that encourages semantic consistency for non-sarcastic samples while suppressing misleading consistency in sarcastic cases. The proposed framework is trained end-to-end with a multi-objective learning strategy that jointly optimizes multimodal classification and auxiliary unimodal supervision. Extensive experiments on MMSD and MMSD2.0 demonstrate that the proposed method consistently outperforms strong baselines.

cs.CL↗
arXiv2026

Robust Incomplete Multimodal Sentiment Analysis via Iterative Proxy Correction

Multimodal sentiment analysis aims to infer affective states by integrating language, visual, and acoustic cues. However, real-world multimodal inputs are often incomplete or corrupted, which can weaken cross-modal complementarity and introduce misleading information into downstream fusion. Existing proxy-based methods for incomplete MSA commonly rely on one-shot proxy construction to compensate for degraded language information, but the generated proxy may be coarse or unreliable at initialization. Prematurely injecting such a proxy into multimodal reasoning can propagate initial errors and compromise sentiment prediction. To address this limitation, we propose an iterative proxy correction framework for robust incomplete MSA. Our method constructs a language-oriented proxy from non-language modalities and progressively refines it under multimodal context through gated residual correction. The corrected proxy is then adaptively fused with the observed language representation according to an estimated language reliability score, allowing the model to balance proxy-based compensation and trustworthy linguistic evidence. In addition, we introduce a stage-wise latent correction objective that uses the complete language representation as a training-time semantic anchor to stabilize the proxy refinement trajectory. Extensive experiments on MOSI, MOSEI, and SIMS under diverse missing-modality settings demonstrate that the proposed framework consistently outperforms competitive baselines and achieves robust sentiment prediction under incomplete inputs.

cs.CL↗
arXiv2026

Simulating Dispute Mediation with LLM-Based Agents for Legal Research

Legal dispute mediation plays a crucial role in resolving civil disputes, yet its empirical study is limited by privacy constraints and complex multivariate interactions. To address this limitation, we present AgentMediation, the first LLM-based agent framework for simulating dispute mediation. It simulates realistic mediation processes grounded in real-world disputes and enables controlled experimentation on key variables such as disputant strategies, dispute causes, and mediator expertise. Our empirical analysis reveals patterns consistent with sociological theories, including Group Polarization and Surface-level Consensus. As a comprehensive and extensible platform, AgentMediation paves the way for deeper integration of social science and AI in legal research.

cs.CY↗
arXiv2026

Agent-Based Test Assertion Generation via Diverse Perspective Aggregation

Test assertions are critical elements of unit tests, serving as checkpoints to validate expected behavior and ensure software correctness. Numerous techniques have been proposed to automate assertion generation, with recent progress notably driven by large language models (LLMs). Despite the promise, existing approaches such as ChatAssert suffer from modest accuracy, heavy reliance on oversampling, and vulnerability to model randomness due to one-shot prompting. To address these limitations, we propose AssertMate, a novel agent-based assertion generation framework that enhances the quality and reliability of LLM-generated assertions through three key components: (1) actual value construction that identifies assertion targets via static analysis and type-aware heuristics; (2) multi-perspective expected value prediction using code generation, retrieval-augmented generation (RAG), and chain-of-thought (CoT) reasoning agents; and (3) an LLM-as-a-Judge collaboration mechanism to select the most appropriate assertion. Evaluation on the Defects4J benchmark demonstrates that AssertMate significantly outperforms state-of-the-art techniques in compilation success and pass rates, along with substantially higher bug detection capabilities. Integration with EvoSuite further validates AssertMate's practicality, yielding superior mutation coverage and kill counts. Ablation studies reveal that each of the three components makes a significant and complementary contribution to the overall performance. This work affirms the great potential of aggregating diverse perspectives to enhance the effectiveness of LLM-based assertion generation.

cs.SE↗
arXiv2026

Learning Globally Reusable Skills for Coding Agents

Automated skill evolution enables Large Language Model (LLM) agents to continuously improve without expensive retraining. However, existing approaches typically treat skill evolution as a sequence of local updates, overlooking relationships among skills and often producing overfitted skill updates that fail to generalize across tasks. We propose GSE, a globalized skill evolution framework that jointly optimizes skill compatibility and skill generalization. To preserve consistency across the skill bank, GSE maintains a Skill Relation Graph (SRG) that explicitly models and co-evolves inter-skill relationships. To improve generalization, GSE performs cluster-based skill consolidation to abstract reusable capabilities from local updates and employs replay-driven verification to prevent overfitting and behavioral regressions. We evaluate GSE on two representative software engineering tasks: bug-revealing test generation and false-positive bug report filtering. Across two state-of-the-art coding agents, OpenHands and mini-SWE-agent, GSE consistently achieves the best precision, recall, and F1-score. Compared with existing evolution techniques, GSE improves precision and recall by 6.1%~34.1% and 31.8%~180.0% for test generation, and by 15.4%~96.4% and 13.1%~19.8% for false-positive filtering. Deployment on an internal industrial agent further yields a 61.4% improvement in F1-score, demonstrating the effectiveness and generalizability of GSE for evolving effective skills.

cs.SE↗
arXiv2026

SieveIVF: Threshold-Aware IVF Execution for Large-Scale Training Data Deduplication

Embedding-based training data deduplication retrieves candidate duplicate edges above an application similarity threshold, but fixed-probe inverted-file (IVF) search ignores this predicate when giving every query the same partition budget. Across four Hunyuan workloads, qualifying neighbors appear early despite sharply varying search depths. We present SieveIVF, a threshold-aware IVF executor that stops after $W$ consecutive searches find no qualifying candidate. The systems challenge is to preserve partition-major batching when each query's remaining work depends on prior results. Continuous batching groups ready queries by partition. A lookahead scheduler layers on top, exposing only work committed by the stopping rule to increase concurrency without changing stopping decisions or returned results. We implement SieveIVF in Lance. At $W=8$, SieveIVF is $4.1$--$7.6\times$ faster than fixed-probe IVF on four 10M Hunyuan workloads and $6.1$--$8.4\times$ faster on two public 100M workloads under the same index and search parameters, with pooled filtered top-10 recall losses of $0.03$--$1.13$ percentage points on Hunyuan and $1.43$--$2.29$ percentage points on the public workloads. These results show how an application predicate can guide IVF work allocation without changing the index or bounded top-$k$ interface.

cs.DB↗
arXiv2026

Machine Learning-Guided Screening of Advantageous Solvents for Solid Polymer Electrolytes in Lithium Metal Batteries

Trace residual solvents in solid polymer electrolytes (SPEs) significantly affect electrolyte and interface properties, where optimal selection enhances ionic conductivity and transference numbers. However, solvent complexity hinders general screening methods. We establish a universal criterion linking electronic (HOMO, LUMO) and macroscopic properties (dielectric constant, dipole moment, polarizability) via machine learning on an approximately 10,000-solvent dataset from high-throughput DFT. Two solvents, N-methoxy-N-methyl-2,2,2-trifluoroacetamide and 2,2,2-trifluoro-N,N-dimethylacetamide, were identified. Experimental incorporation of trace N-methoxy-N-methyl-2,2,2-trifluoroacetamide into a poly(vinylidene fluoride-co-hexafluoropropylene) matrix achieves a 4.5 V window, 5.5x10^-4 S cm^-1 conductivity (30 C), and 0.78 Li+ transference number. The cell retains 86.7% capacity over 500 cycles (LiFePO4) and 98.7% after 200 cycles at 2C (LiNi0.9Co0.05Mn0.05O2), outperforming 2,2,2-trifluoro-N,N-dimethylacetamide, dimethylformamide, N-methyl-2-pyrrolidone, and dimethyl sulfoxide. This synergy enables balanced ion transport, wide stability, and cycling durability, advancing safer, high-energy lithium metal batteries. Our integrated approach establishes a solvent screening paradigm for rational SPE design, accelerating next-generation battery development.

cond-mat.mtrl-sci↗
arXiv2026

Constant-depth adaptive preparation of Dicke and symmetric states

Efficient preparation of Dicke states and, more generally, permutation-symmetric states is important for quantum metrology, quantum networking, and collective quantum information processing. Measurements and classical feedforward enable low-depth preparations of these states, with a cost of ancillary qubits. In this work, we introduce an exact constant-depth adaptive preparation protocol for arbitrary Dicke-$(n,k)$ states and further symmetric states. We first provide a protocol preparing the uniform subset superposition state, as a primitive, using constant-depth adaptive circuit with $O(k^2\log^2 n)$ ancillary qubits and success probability at least $1/k$. This yields an exact, probabilistic, constant-depth Dicke-state preparation protocol using $O\left(n^2+k^2\log^2 n+kn\log n\log\log n\right)$ ancillary qubits. Parallel repetition suppresses the failure probability exponentially without increasing the quantum depth. Moreover, the uniform subset superposition state is also of independent interest as the uniform vertex state of the Johnson graph and as the compact uniform subset state appearing in quantum-walk and topological-data-analysis algorithms. We further establish a general lifting framework that coherently combines clean unitary Dicke-state preparation circuits to prepare arbitrary symmetric states with only polynomial ancillary overhead. Combined with recent constant-depth unitary Dicke-state constructions, this gives an exact constant-depth preparation protocol for arbitrary $n$-qubit symmetric states using $O(n^3\sqrt{\log n})$ ancillary qubits.

quant-ph↗
arXiv2026

Evaluating Fuzz Testing for Reinforcement Learning Agents

Reinforcement Learning (RL) agents are increasingly deployed in safety-critical domains such as robotics, autonomous driving, and drone control, where unexpected behaviors may lead to severe real-world consequences. Fuzz testing has recently emerged as a promising method for exploring the vast state spaces of RL agents and exposing crashes. Although numerous RL fuzzing methods have been proposed, existing studies often differ in evaluation settings, baselines, and metrics, making it difficult to draw reliable conclusions about their relative effectiveness and practical usefulness. To address this gap, we present the first comprehensive empirical study that systematically evaluates RL fuzzing methods from four complementary perspectives: effectiveness, diversity, efficiency, and practical utility. We benchmark five state-of-the-art methods alongside random testing under unified configurations across three environments of increasing complexity (MountainCar, BipedalWalker, and CARLA), and further assess the downstream usefulness of detected crashes for agent robustness improvement and safety monitoring. Our results reveal several key insights. For instance,throughput-oriented methods like MDPFuzz demonstrate superior effectiveness and efficiency in crash discovery, while methods explicitly designed to encourage exploration like SeqDivFuzz excel at uncovering diverse crash behaviors. We also show that fuzzing-generated crashes can meaningfully improve agent robustness and enable accurate safety monitoring with strong cross-method generalization. Beyond these empirical findings, we distill actionable guidance for both researchers and practitioners, highlighting the benefits of combining complementary fuzzing strategies and adopting multi-level diversity analysis to achieve more comprehensive and practical RL testing.

cs.LG↗
arXiv2026

Context Matters: Improving the Practical Reliability of LLM-Based Unit Test Generation

Automated unit test generation has recently benefited from advances in large language models (LLMs), yet our industrial deployments reveal a persistent gap between promising research results and practical usability. In real-world projects with complex frameworks and cross-file dependencies, LLM-generated tests frequently fail to compile, require costly manual repair, or provide unstable coverage improvements. This paper reports our experience in designing, deploying, and evaluating CATGen, a context-aware workflow for LLM-based unit test generation, informed by repeated industrial failures and refinements. Rather than relying on LLMs to infer incomplete project context, we found that compilation robustness critically depends on making project-level dependencies explicit, stabilizing test class scaffolding, and replacing iterative LLM-based repair with lightweight static analysis. These experience-driven insights shaped CATGen's multi-stage design, which combines structured context retrieval, deterministic test skeleton construction, and program analysis-based post-processing. We evaluate CATGen on real-world complex focal methods from proprietary industrial projects and additionally on the Defects4J benchmark to assess generalizability. Across both settings, CATGen substantially improves compilation success and structural coverage while significantly reducing generation time and token consumption compared to existing LLM-based approaches. Our results demonstrate that reliable LLM-based unit test generation in practice depends less on prompt engineering alone and more on systematic engineering support grounded in real-world development constraints.

cs.SE↗
arXiv2026

KernelDiag: Agent-Based Root Cause Diagnosis for Kernel Crashes

The Linux kernel is one of the most complex software systems, where automated fuzzing continuously exposes thousands of crashes, yet root-cause diagnosis remains a manual and time-consuming bottleneck. Existing LLM-based root cause analysis (RCA) techniques, effective for distributed systems, do not readily generalize to kernel debugging due to sparse low-level artifacts, heterogeneous diagnostic evidence (e.g., syscalls, logs, and crash reports), and complex non-linear fault propagation that demands fine-grained method-level reasoning. To address these challenges, we propose KernelDiag, an agent-based framework for kernel root-cause diagnosis via structured causal reasoning. KernelDiag first aligns heterogeneous diagnostic artifacts through log-to-code mapping, and then employs artifact-specialized agents to iteratively reason over source-level program semantics and crash-specific kernel configurations. The inferred causal dependencies are incrementally organized into structured Evidence Graphs, enabling accurate faulty-method localization and causal explanations. We evaluate KernelDiag on the real-world KGYM benchmark. KernelDiag consistently outperforms state-of-the-art localization approaches at both file and method levels, achieving significant improvements in Top@k accuracy, including up to 4x and 2x gains in challenging settings without explicit hints. Furthermore, both human and LLM-assisted evaluations show that KernelDiag generates accurate, coherent, and actionable diagnostic explanations. Overall, this work lays the foundation for automated kernel root-cause diagnosis by bridging low-level diagnostic evidence with source-level causal reasoning.

cs.SE↗
arXiv2026

GapForge: Directed Compiler Fuzzing via Coverage-Gap Analysis

Modern compiler codebases (e.g., GCC and LLVM) are large and complex, making comprehensive coverage across diverse code regions highly challenging. Most existing test generation techniques ignore characteristics of the target code, producing test programs that exercise only a limited subset of it. Consequently, substantial compiler regions remain insufficiently tested, leaving persistent long-tail coverage gaps that survive across releases. Even existing white-box techniques achieve limited coverage on large-scale compilers. To improve compiler coverage, especially for hard-to-reach edge regions, we present GapForge, a targeted LLM-based test generation technique that reasons about coverage gaps. Unlike program-driven techniques that generate diverse inputs without modeling which regions they exercise, and unlike whole-file summarization that yields coarse guidance, GapForge treats coverage gaps as explicit region-level targets in three steps. First, it prioritizes files via coverage-driven scoring that favors large, undercovered files. Second, it pairs each uncovered line span with its enclosing covered context and performs path-difference analysis to infer fine-grained triggering requirements: the program structures and compilation options needed to reach the uncovered region. Third, it synthesizes prompts from these requirements and previously failed prompts, using coverage feedback to guide next-round selection. On GCC 14.3.0 and LLVM 19.1.0, GapForge significantly outperforms eight state-of-the-art techniques. Within 72 hours, it achieves 68.13% and 69.11% coverage on core compiler modules in GCC and LLVM, surpassing the white-box technique WhiteFox by 24,736 and 19,798 additional lines, respectively. Moreover, GapForge discovers 12 real-world compiler failures (5 in GCC, 7 in LLVM), including 8 crashes and 4 miscompilations, with each component contributing to its performance.

cs.SE↗
arXiv2026

Strict Fairness at What Cost? Envy-Free Contracts with Subsidies

We study algorithmic fair contract design, where a principal designs task-level contracts and fairly delegates a set of tasks to a set of agents. Prior work reveals a fairness-revenue dilemma: exact envy-free (EF) contracts may have an unbounded price of fairness (PoF), while approximate notions avoid this unboundedness only by weakening strict fairness. To address this dilemma, we propose a novel scheme, called {\it Envy-free Contracts with Subsidies} (EFS), in which the principal may additionally offer agent-specific subsidies to restore strict fairness. Our main technical result is a tight characterization of the price of fairness for EFS contracts. In sharp contrast to EF contracts, whose PoF can be unbounded, we show that the PoF of EFS contracts is $n^{n+O(1)}$, where $n$ is the number of agents. Moreover, EFS contracts can outperform EF contracts by an arbitrarily large factor in terms of the principal's revenue. Finally, we present the complexity landscape: computing optimal EFS contracts is NP-hard in general, whereas a polynomial-time algorithm exists when the number of tasks is constant.

cs.GT↗
arXiv2026

Algorithmic Fair Contracts

We initiate the algorithmic study of fair contract design. A principal assigns multiple tasks to heterogeneous agents and chooses task-level linear contracts; agents differ in costs and success probabilities, and fairness requires each agent to prefer her own task-contract bundle to any other agent's. Unlike envy-free allocations of indivisible items, envy-free full-allocation contracts always exist, but optimizing revenue under this constraint is computationally difficult: no polynomial-time algorithm can achieve any constant-factor approximation in general. We therefore identify tractable regimes. With a constant number of tasks, optimal EF, EF1, and $ε$-EF contracts are computable in polynomial time. With a constant number of agents, exact EF remains hard, even for three agents, while EF1 and $ε$-EF admit additive FPTAS against the EF benchmark. We also show that exact EF can have an unbounded price of fairness, whereas $ε$-EF and EF1 can restore bounded revenue loss.

cs.GT↗