Searcharxiv⌕ Search

arXiv subjects

Chen Shen

Publications and source records attributed to Chen Shen.

At least 55 records · Page 3Linked to original sources

SCOUT: Active Information Foraging for Long-Text Understanding with Decoupled Epistemic States

Long-Text Understanding (LTU) at million-token scale requires balancing reasoning fidelity with computational efficiency. Frontier long-context LLMs can process millions of token contexts end-to-end, but they suffer from high token consumption and attention dilution. In parallel, specialized LTU agents often sacrifice fidelity through task-agnostic abstractions like graph construction or indexing. We identify a key insight for LTU: query-relevant information is typically sparse relative to the full document, so effective reasoning should rely on a query-sufficient subset rather than the entire context. To address this, we propose SCOUT, a new paradigm for LTU that shifts from passive processing to active information foraging. It treats the document as an explorable environment and answers from a compact, provenance-grounded epistemic state. Guided by state-level gap diagnosis, SCOUT adaptively alternates between coarse-to-fine exploration and anchored state updates that progressively contract its epistemic state toward query sufficiency. Experiments show that SCOUT matches state-of-the-art proprietary models while reducing token consumption by up to 8x. Moreover, SCOUT remains stable as context length scales, substantially alleviating the practical cost-performance trade-off.

cs.CL↗

OpenAI GPT-5 System Card

This is the system card published alongside the OpenAI GPT-5 launch, August 2025. GPT-5 is a unified system with a smart and fast model that answers most questions, a deeper reasoning model for harder problems, and a real-time router that quickly decides which model to use based on conversation type, complexity, tool needs, and explicit intent (for example, if you say 'think hard about this' in the prompt). The router is continuously trained on real signals, including when users switch models, preference rates for responses, and measured correctness, improving over time. Once usage limits are reached, a mini version of each model handles remaining queries. This system card focuses primarily on gpt-5-thinking and gpt-5-main, while evaluations for other models are available in the appendix. The GPT-5 system not only outperforms previous models on benchmarks and answers questions more quickly, but -- more importantly -- is more useful for real-world queries. We've made significant advances in reducing hallucinations, improving instruction following, and minimizing sycophancy, and have leveled up GPT-5's performance in three of ChatGPT's most common uses: writing, coding, and health. All of the GPT-5 models additionally feature safe-completions, our latest approach to safety training to prevent disallowed content. Similarly to ChatGPT agent, we have decided to treat gpt-5-thinking as High capability in the Biological and Chemical domain under our Preparedness Framework, activating the associated safeguards. While we do not have definitive evidence that this model could meaningfully help a novice to create severe biological harm -- our defined threshold for High capability -- we have chosen to take a precautionary approach.

cs.CL↗

OpenAI o1 System Card

The o1 model series is trained with large-scale reinforcement learning to reason using chain of thought. These advanced reasoning capabilities provide new avenues for improving the safety and robustness of our models. In particular, our models can reason about our safety policies in context when responding to potentially unsafe prompts, through deliberative alignment. This leads to state-of-the-art performance on certain benchmarks for risks such as generating illicit advice, choosing stereotyped responses, and succumbing to known jailbreaks. Training models to incorporate a chain of thought before answering has the potential to unlock substantial benefits, while also increasing potential risks that stem from heightened intelligence. Our results underscore the need for building robust alignment methods, extensively stress-testing their efficacy, and maintaining meticulous risk management protocols. This report outlines the safety work carried out for the OpenAI o1 and OpenAI o1-mini models, including safety evaluations, external red teaming, and Preparedness Framework evaluations.

cs.AI↗

To Diff or Not to Diff? Structure-Aware and Adaptive Output Formats for Efficient LLM-based Code Editing

Large Language Models (LLMs) are increasingly used for code editing, yet the prevalent full-code generation paradigm suffers from severe efficiency bottlenecks, posing challenges for interactive coding assistants that demand low latency and cost. Despite the predominant focus on scaling model capabilities, the edit format itself has been largely overlooked in model training. In this paper, we begin with a systematic study of conventional diff formats and reveal that fragile offsets and fragmented hunks make generation highly unnatural for LLMs. To address it, we introduce BlockDiff and FuncDiff, two structure-aware diff formats that represent changes as block-level rewrites of syntactically coherent units such as control structures and functions. Furthermore, we propose AdaEdit, a general adaptive edit strategy that trains LLMs to dynamically choose the most token-efficient format between a given diff format and full code. Extensive experiments demonstrate that AdaEdit paired with structure-aware diff formats consistently matches the accuracy of full-code generation, while reducing both latency and cost by over 30% on long-code editing tasks.

cs.SE↗

Frequency Security Assessment in Power Systems With High Penetration of Renewables Considering Spatio-Temporal Frequency Distribution

The increasing integration of renewable energy sources exacerbates the spatial and temporal differences in frequency across the power system, posing a serious challenge to the accurate and efficient assessment of system frequency security. To address this issue, a generic effective nodal frequency (ENF) model is first established to concisely characterize nodal frequency dynamics. This model is featured by the effective nodal inertia (ENI), damping, and primary regulation parameters, which retain only the dominant constant component governing nodal frequency dynamic performance. This model enables the tractable analytical formulation of nodal frequency trajectory and the key frequency security indicators. Quantitative analysis under the temporary power disturbance condition reveals that the ENI is the most influential parameter governing frequency security. Consequently, the critical nodal inertia for ensuring nodal frequency security is analytically derived. A system-level frequency security index based on the actual ENI and critical nodal inertia is proposed. On the basis of the proposed index, the system frequency security assessment is carried out with the procedure of ``offline calculation and online evaluation'', which is achieved using a lookup table approach and an interpolation method. Simulations on the modified IEEE 39-bus system verify the effectiveness of the proposed assessment method.

eess.SY↗

Bootstrapping Code Translation with Weighted Multilanguage Exploration

Code translation across multiple programming languages is essential yet challenging due to two vital obstacles: scarcity of parallel data paired with executable test oracles, and optimization imbalance when handling diverse language pairs. We propose BootTrans, a bootstrapping method that resolves both obstacles. Its key idea is to leverage the functional invariance and cross-lingual portability of test suites, adapting abundant pivot-language unit tests to serve as universal verification oracles for multilingual reinforcement learning (RL) training. Our method introduces a dual-pool architecture with seed and exploration pools to progressively expand training data via execution-guided experience collection. Furthermore, we design a language-aware weighting mechanism that dynamically prioritizes harder translation directions based on relative performance across sibling languages, mitigating optimization imbalance. Extensive experiments on the HumanEval-X and TransCoder-Test benchmarks demonstrate substantial improvements over baseline LLMs across all translation directions, with ablation studies validating the effectiveness of both bootstrapping and weighting components.

cs.SE↗

Blue Data Intelligence Layer: Streaming Data and Agents for Multi-source Multi-modal Data-Centric Applications

NL2SQL systems aim to address the growing need for natural language interaction with data. However, real-world information rarely maps to a single SQL query because (1) users express queries iteratively (2) questions often span multiple data sources beyond the closed-world assumption of a single database, and (3) queries frequently rely on commonsense or external knowledge. Consequently, satisfying realistic data needs require integrating heterogeneous sources, modalities, and contextual data. In this paper, we present Blue's Data Intelligence Layer (DIL) designed to support multi-source, multi-modal, and data-centric applications. Blue is a compound AI system that orchestrates agents and data for enterprise settings. DIL serves as the data intelligence layer for agentic data processing, to bridge the semantic gap between user intent and available information by unifying structured enterprise data, world knowledge accessible through LLMs, and personal context obtained through interaction. At the core of DIL is a data registry that stores metadata for diverse data sources and modalities to enable both native and natural language queries. DIL treats LLMs, the Web, and the User as source 'databases', each with their own query interface, elevating them to first-class data sources. DIL relies on data planners to transform user queries into executable query plans. These plans are declarative abstractions that unify relational operators with other operators spanning multiple modalities. DIL planners support decomposition of complex requests into subqueries, retrieval from diverse sources, and finally reasoning and integration to produce final results. We demonstrate DIL through two interactive scenarios in which user queries dynamically trigger multi-source retrieval, cross-modal reasoning, and result synthesis, illustrating how compound AI systems can move beyond single database NL2SQL.

cs.AI↗

On the Step Length Confounding in LLM Reasoning Data Selection

Large reasoning models have recently demonstrated strong performance on complex tasks that require long chain-of-thought reasoning, through supervised fine-tuning on large-scale and high-quality datasets. To construct such datasets, existing pipelines generate long reasoning data from more capable Large Language Models (LLMs) and apply manually heuristic or naturalness-based selection methods to filter high-quality samples. Despite the proven effectiveness of naturalness-based data selection, which ranks data by the average log probability assigned by LLMs, our analysis shows that, when applied to LLM reasoning datasets, it systematically prefers samples with longer reasoning steps (i.e., more tokens per step) rather than higher-quality ones, a phenomenon we term step length confounding. Through quantitative analysis, we attribute this phenomenon to low-probability first tokens in reasoning steps; longer steps dilute their influence, thereby inflating the average log probabilities. To address this issue, we propose two variant methods: ASLEC-DROP, which drops first-token probabilities when computing average log probability, and ASLEC-CASL, which applies a causal debiasing regression to remove the first tokens' confounding effect. Experiments across four LLMs and five evaluation benchmarks demonstrate the effectiveness of our approach in mitigating the step length confounding problem.

cs.CL↗

Multiprotocol Wireless Timer Synchronization for IoT Systems

Accurate time synchronization is essential for Internet of Things (IoT) systems, where multiple distributed nodes must share a common time base for coordinated sensing and data fusion. However, conventional synchronization approaches suffer from nondeterministic transmission latency, limited precision, or restricted bidirectional functionality. This paper presents a protocol-independent wireless timer synchronization method that exploits radio timeslots to transmit precisely timestamped beacons in a proprietary radio mode. By decoupling synchronization from upper-layer packet retransmissions and leveraging hardware-timed radio events, the proposed approach significantly reduces scheduling uncertainty and achieves nanosecond-level synchronization accuracy. Comprehensive experiments evaluate the impacts of synchronization frequency, RSSI, BLE connection interval, and throughput on synchronization performance. The results demonstrate that an optimal synchronization frequency of 1000 Hz yields an approximately 20 ns delay in the absence of communication stack activity while maintaining sub-500 ns accuracy under most realistic BLE traffic conditions. Furthermore, larger connection intervals, lower application throughput, and higher RSSI consistently improve synchronization quality by reducing radio resource contention and packet loss. The proposed scheme provides a general and high-precision synchronization solution suitable for resource-constrained IoT systems.

cs.NI↗

ART: Attention Replacement Technique to Improve Factuality in LLMs

Hallucination in large language models (LLMs) continues to be a significant issue, particularly in tasks like question answering, where models often generate plausible yet incorrect or irrelevant information. Although various methods have been proposed to mitigate hallucinations, the relationship between attention patterns and hallucinations has not been fully explored. In this paper, we analyze the distribution of attention scores across each layer and attention head of LLMs, revealing a common and intriguing phenomenon: shallow layers of LLMs primarily rely on uniform attention patterns, where the model distributes its attention evenly across the entire sequence. This uniform attention pattern can lead to hallucinations, as the model fails to focus on the most relevant information. To mitigate this issue, we propose a training-free method called Attention Replacement Technique (ART), which replaces these uniform attention patterns in the shallow layers with local attention patterns. This change directs the model to focus more on the relevant contexts, thus reducing hallucinations. Through extensive experiments, ART demonstrates significant reductions in hallucinations across multiple LLM architectures, proving its effectiveness and generalizability without requiring fine-tuning or additional training data.

cs.CL↗

Typical Scenarios Generation Method Considering System-level Characteristics of Power System

This paper proposes a method for generating typical scenarios based on system-level macroscopic characteristics of power system and considering its stability properties. First, considering uncertainties such as renewable energy generation in power-electronics-dominated power systems, multidimensional scaling is used to construct an electrical coordinate system. Based on this, system-level characteristics of the distribution of physical quantities, such as power generation and load, are characterized. Furthermore, a method for generating typical scenarios based on the system's system-level characteristics and stability properties is proposed. For the obtained joint probability distribution of system-level characteristics, weighted Mahalanobis distance can be used to predict the stability properties of random scenarios. Finally, the typicality and representativeness of the scenarios generated by the proposed method with respect to stability properties are verified on the CSEE benchmark case, and stability prediction for random scenarios is achieved using a probabilistic testing method.

eess.SY↗

Accelerated Design of Mechanically Hard Magnetically Soft High-entropy Alloys via Multi-objective Bayesian Optimization

Designing high-entropy alloys (HEAs) that are both mechanically hard and possess soft magnetic properties is inherently challenging, as a trade-off is needed for mechanical and magnetic properties. In this study, we optimize HEA compositions using a multi-objective Bayesian optimization (MOBO) framework to achieve simultaneous optimal mechanical and magnetic properties. An ensemble surrogate model is constructed to enhance the accuracy of machine learning surrogate models, while an efficient sampling strategy combining Monte Carlo sampling and acquisition function is applied to explore the high-dimensional compositional space. The implemented MOBO strategy successfully identifies Pareto-optimal compositions with enhanced mechanical and magnetic properties. The ensemble model provides robust and reliable predictions, and the sampling approach reduces the likelihood of entrapment in local optima. Our findings highlight specific elemental combinations that meet the dual design objectives, offering guidance for the synthesis of next-generation HEAs.

cond-mat.mtrl-sci↗

Composer 2 Technical Report

Composer 2 is a specialized model designed for agentic software engineering. The model demonstrates strong long-term planning and coding intelligence while maintaining the ability to efficiently solve problems for interactive use. The model is trained in two phases: first, continued pretraining to improve the model's knowledge and latent coding ability, followed by large-scale reinforcement learning to improve end-to-end coding performance through stronger reasoning, accurate multi-step execution, and coherence on long-horizon realistic coding problems. We develop infrastructure to support training in the same Cursor harness that is used by the deployed model, with equivalent tools and structure, and use environments that match real problems closely. To measure the ability of the model on increasingly difficult tasks, we introduce a benchmark derived from real software engineering problems in large codebases including our own. Composer 2 is a frontier-level coding model and demonstrates a process for training strong domain-specialized models. On our CursorBench evaluations the model achieves a major improvement in accuracy compared to previous Composer models (61.3). On public benchmarks the model scores 61.7 on Terminal-Bench and 73.7 on SWE-bench Multilingual in our harness, comparable to state-of-the-art systems.

cs.SE↗

Grid-following and Grid-forming Switching Control for Grid-connected Inverters Considering Small-signal Security Region

In high-penetration renewable power systems with complex and highly variable operating scenarios, grid-connected inverters (GCIs) may transition between different control modes to adapt to diverse grid conditions. Among these, the switching between grid-following (GFL) and grid-forming (GFM) control modes is particularly critical. Nevertheless, safe and robust GFL-GFM switching control strategies for GCIs remain largely unexplored. To overcome this challenge, this paper establishes a full-order small-signal state-space model for the GFL-GFM switched system, precisely reflecting all internal circuit and control dynamics. Subsequently, the small-signal security region (SSSR) of the switched system is defined and characterized, followed by an in-depth investigation into the multi-parameter impacts on the SSSRs and internal stability margin distributions (ISMDs). Furthermore, a novel comprehensive stability index (CSI) is proposed by integrating the stability margin, parameter sensitivity, and boundary distance. Based on this CSI, a multi-objective adaptive GFL-GFM switching control strategy is designed to guarantee the dynamic security and robustness of the system. Finally, the proposed SSSR analysis method for the GFL-GFM switched system and the designed CSI-based switching control mechanism are validated through electromagnetic transient (EMT) simulations.

eess.SY↗

Exploration enhances cooperation in the multi-agent communication system

Designing protocols enhancing cooperation for multi-agent systems remains a grand challenge. Cheap talk, defined as costless, non-binding communication before formal action, serves as a pivotal solution. However, existing theoretical frameworks often exclude random exploration, or noise, for analytical tractability, leaving its functional impact on system performance largely unexplored. To bridge this gap, we propose a two-stage evolutionary game-theoretical model, integrating signalling with a donation game, with exploration explicitly incorporated into the decision-making. Our agent-based simulations across topologies reveal a universal optimal exploration rate that maximises system-wide cooperation. Mechanistically, moderate exploration undermines the stability of defection and catalyses the self-organised cooperative alliances, facilitating their cyclic success. Moreover, the cooperation peak is enabled by the delicate balance between oscillation period and amplification. Our findings suggest that rather than pursuing deterministic rigidity, embracing strategic exploration, as a form of engineered randomness, is essential to sustain cooperation and realise optimal performance in communication-based intelligent systems.

cs.MA↗

Where Did This Sentence Come From? Tracing Provenance in LLM Reasoning Distillation

Reasoning distillation has attracted increasing attention. It typically leverages a large teacher model to generate reasoning paths, which are then used to fine-tune a student model so that it mimics the teacher's behavior in training contexts. However, previous approaches have lacked a detailed analysis of the origins of the distilled model's capabilities. It remains unclear whether the student can maintain consistent behaviors with the teacher in novel test-time contexts, or whether it regresses to its original output patterns, raising concerns about the generalization of distillation models. To analyse this question, we introduce a cross-model Reasoning Distillation Provenance Tracing framework. For each action (e.g., a sentence) produced by the distilled model, we obtain the predictive probabilities assigned by the teacher, the original student, and the distilled model under the same context. By comparing these probabilities, we classify each action into different categories. By systematically disentangling the provenance of each action, we experimentally demonstrate that, in test-time contexts, the distilled model can indeed generate teacher-originated actions, which correlate with and plausibly explain observed performance on distilled model. Building on this analysis, we further propose a teacher-guided data selection method. Unlike prior approach that rely on heuristics, our method directly compares teacher-student divergences on the training data, providing a principled selection criterion. We validate the effectiveness of our approach across multiple representative teacher models and diverse student models. The results highlight the utility of our provenance-tracing framework and underscore its promise for reasoning distillation. We hope to share Reasoning Distillation Provenance Tracing and our insights into reasoning distillation with the community.

cs.CL↗

Evolution of fairness in hybrid populations with specialised AI agents

Fairness in hybrid societies hinges on a simple choice: should AI be a generous host or a strict gatekeeper? Moving beyond symmetric models, we show that asymmetric social structures--like those in hiring, regulation, and negotiation--AI that guards fairness outperforms AI that gifts it. We bridge this gap with a bipartite hybrid population model of the Ultimatum Game, separating humans and AI into distinct proposer and receiver groups. We first introduce Samaritan AI agents, which act as either unconditional fair proposers or strict receivers. Our results reveal a striking asymmetry: Samaritan AI receivers drive population-wide fairness far more effectively than Samaritan AI proposers. To overcome the limitations of the Samaritan AI proposer, we design the Discriminatory AI proposer, which predicts co-players' expectations and only offers fair portions to those with high acceptance thresholds. Our results demonstrate that this Discriminatory AI outperforms both types of Samaritan AI, especially in strong selection scenarios. It not only sustains fairness across both populations but also significantly lowers the critical mass of agents required to reach an equitable steady state. By transitioning from unconditional modelling to strategic enforcement, our work provides a pivotal framework for deploying asymmetric AIs in the increasingly hybrid society.

cs.MA↗

Information-Theoretic Multi-Model Fusion for Target-Oriented Adaptive Sampling in Materials Design

Target-oriented discovery under limited evaluation budgets requires making reliable progress in high-dimensional, heterogeneous design spaces where each new measurement is costly, whether experimental or high-fidelity simulation. We present an information-theoretic framework for target-oriented adaptive sampling that reframes optimization as trajectory discovery: instead of approximating the full response surface, the method maintains and refines a low-entropy information state that concentrates search on target-relevant directions. The approach couples data, model beliefs, and physics/structure priors through dimension-aware information budgeting, adaptive bootstrapped distillation over a heterogeneous surrogate reservoir, and structure-aware candidate manifold analysis with Kalman-inspired multi-model fusion to balance consensus-driven exploitation and disagreement-driven exploration. Evaluated under a single unified protocol without dataset-specific tuning, the framework improves sample efficiency and reliability across 14 single- and multi-objective materials design tasks spanning candidate pools from $600$ to $4 \times 10^6$ and feature dimensions from $10$ to $10^3$, typically reaching top-performing regions within 100 evaluations. Complementary 20-dimensional synthetic benchmarks (Ackley, Rastrigin, Schwefel) further demonstrate robustness to rugged and multimodal landscapes.

cs.LG↗