Xinchi Chen

Danilo Ribeiro, Shen Wang, Xiaofei Ma et al. · amazon-science

Large language models have achieved high performance on various question answering (QA) benchmarks, but the explainability of their output remains elusive. Structured explanations, called entailment trees, were recently suggested as a way to explain and inspect a QA system's answer. In order to better generate such entailment trees, we propose an architecture called Iterative Retrieval-Generation Reasoner (IRGR). Our model is able to explain a given hypothesis by systematically generating a step-by-step explanation from textual premises. The IRGR model iteratively searches for suitable premises, constructing a single entailment step at a time. Contrary to previous approaches, our method combines generation steps and retrieval of premises, allowing the model to leverage intermediate conclusions, and mitigating the input size limit of baseline encoder-decoder models. We conduct experiments using the EntailmentBank dataset, where we outperform existing benchmarks on premise retrieval and entailment tree generation, with around 300% gain in overall correctness.

Nex-AGI Team, Yuxuan Cai, Lu Chen et al.

The evolution of Large Language Models (LLMs) from passive responders to autonomous agents necessitates a fundamental shift in learning paradigms -- from static imitation to incentive-driven decision making. However, this transition is significantly impeded by the lack of scalable infrastructure capable of constructing high-quality interaction signals for effective policy learning. To address this, we introduce a comprehensive method designed to systematically scale the diversity and complexity of interactive environments. Our method realizes this scaling by addressing three orthogonal dimensions: (1) Complexity: NexAU, a flexible agent framework that supports building complex agent hierarchies via simple configurations; (2) Diversity: NexA4A automatically generates diverse agent hierarchies from natural language to cover infinite domains; and (3) Fidelity: NexGAP bridges the simulation-reality gap by integrating dynamic real-world environment for grounded trajectories synthesis. We train Nex-N1 upon the diverse and complex interactive environments established by our infrastructure. Empirical results on benchmarks such as SWE-bench and tau2 demonstrate that Nex-N1 consistently outperforms SOTA open-source models and achieves competitive performance against frontier proprietary models on complex agentic tasks. We open-source the Nex ecosystem and model weights to facilitate further research.

Xiyang Hu, Xinchi Chen, Peng Qi et al.

Multilingual information retrieval (IR) is challenging since annotated training data is costly to obtain in many languages. We present an effective method to train multilingual IR systems when only English IR training data and some parallel corpora between English and other languages are available. We leverage parallel and non-parallel corpora to improve the pretrained multilingual language models' cross-lingual transfer ability. We design a semantic contrastive loss to align representations of parallel sentences that share the same semantics in different languages, and a new language contrastive loss to leverage parallel sentence pairs to remove language-specific information in sentence representations from non-parallel corpora. When trained on English IR data with these losses and evaluated zero-shot on non-English data, our model demonstrates significant improvement to prior work on retrieval performance, while it requires much less computational effort. We also demonstrate the value of our model for a practical setting when a parallel corpus is only available for a few languages, but a lack of parallel corpora resources persists for many other low-resource languages. Our model can work well even with a small number of parallel sentences, and be used as an add-on module to any backbones and other tasks.

Jifan Chen, Yuhao Zhang, Lan Liu et al.

There has been great progress in unifying various table-to-text tasks using a single encoder-decoder model trained via multi-task learning (Xie et al., 2022). However, existing methods typically encode task information with a simple dataset name as a prefix to the encoder. This not only limits the effectiveness of multi-task learning, but also hinders the model's ability to generalize to new domains or tasks that were not seen during training, which is crucial for real-world applications. In this paper, we propose compositional task configurations, a set of prompts prepended to the encoder to improve cross-task generalization of unified models. We design the task configurations to explicitly specify the task type, as well as its input and output types. We show that this not only allows the model to better learn shared knowledge across different tasks at training, but also allows us to control the model by composing new configurations that apply novel input-output combinations in a zero-shot manner. We demonstrate via experiments over ten table-to-text tasks that our method outperforms the UnifiedSKG baseline by noticeable margins in both in-domain and zero-shot settings, with average improvements of +0.5 and +12.6 from using a T5-large backbone, respectively.

Jingqi Tong, Mingzhe Li, Hangcheng Li et al.

Great scientists have strong judgement and foresight, closely tied to what we call scientific taste. Here, we use the term to refer to the capacity to judge and propose research ideas with high potential impact. However, most relative research focuses on improving an AI scientist's executive capability, while enhancing an AI's scientific taste remains underexplored. In this work, we propose Reinforcement Learning from Community Feedback (RLCF), a training paradigm that uses large-scale community signals as supervision, and formulate scientific taste learning as a preference modeling and alignment problem. For preference modeling, we train Scientific Judge on 700K field- and time-matched pairs of high- vs. low-citation papers to judge ideas. For preference alignment, using Scientific Judge as a reward model, we train a policy model, Scientific Thinker, to propose research ideas with high potential impact. Experiments show Scientific Judge outperforms SOTA LLMs (e.g., GPT-5.2, Gemini 3 Pro) and generalizes to future-year test, unseen fields, and peer-review preference. Furthermore, Scientific Thinker proposes research ideas with higher potential impact than baselines. Our findings show that AI can learn scientific taste, marking a key step toward reaching human-level AI scientists.

Weiyi Wang, Xinchi Chen, Jingjing Gong et al.

Recent advances in agentic Large Language Models (LLMs) have positioned them as generalist planners capable of reasoning and acting across diverse tasks. However, existing agent benchmarks largely focus on symbolic or weakly grounded environments, leaving their performance in physics-constrained real-world domains underexplored. We introduce AstroReason-Bench, a comprehensive benchmark for evaluating agentic planning in Space Planning Problems (SPP), a family of high-stakes problems with heterogeneous objectives, strict physical constraints, and long-horizon decision-making. AstroReason-Bench integrates multiple scheduling regimes, including ground station communication and agile Earth observation, and provides a unified agent-oriented interaction protocol. Evaluating on a range of state-of-the-art open- and closed-source agentic LLM systems, we find that current agents substantially underperform specialized solvers, highlighting key limitations of generalist planning under realistic constraints. AstroReason-Bench offers a challenging and diagnostic testbed for future agentic research.

Jingqi Tong, Yurong Mou, Hangcheng Li et al.

"Thinking with Text" and "Thinking with Images" paradigm significantly improve the reasoning ability of large language models (LLMs) and Vision Language Models (VLMs). However, these paradigms have inherent limitations. (1) Images capture only single moments and fail to represent dynamic processes or continuous changes, and (2) The separation of text and vision as distinct modalities, hindering unified multimodal understanding and generation. To overcome these limitations, we introduce "Thinking with Video", a new paradigm that leverages video generation models, such as Sora-2, to bridge visual and textual reasoning in a unified temporal framework. To support this exploration, we developed the Video Thinking Benchmark (VideoThinkBench). VideoThinkBench encompasses two task categories: (1) vision-centric tasks (e.g., Eyeballing Puzzles), and (2) text-centric tasks (e.g., subsets of GSM8K, MMMU). Our evaluation establishes Sora-2 as a capable reasoner. On vision-centric tasks, Sora-2 is generally comparable to state-of-the-art (SOTA) VLMs, and even surpasses VLMs on several tasks, such as Eyeballing Games. On text-centric tasks, Sora-2 achieves 92% accuracy on MATH, and 75.53% accuracy on MMMU. Furthermore, we systematically analyse the source of these abilities. We also find that self-consistency and in-context learning can improve Sora-2's performance. In summary, our findings demonstrate that the video generation model is the potential unified multimodal understanding and generation model, positions "thinking with video" as a unified multimodal reasoning paradigm.

Shicheng Fang, Yuxin Wang, XiaoRan Liu et al.

The evolution of Large Language Models (LLMs) into autonomous agents necessitates the management of extensive, dynamic contexts. Current benchmarks, however, remain largely static, relying on passive retrieval tasks that fail to simulate the complexities of agent-environment interaction, such as non-linear reasoning and iterative feedback. To address this, we introduce \textbf{AgentLongBench}, which evaluates agents through simulated environment rollouts based on Lateral Thinking Puzzles. This framework generates rigorous interaction trajectories across knowledge-intensive and knowledge-free scenarios. Experiments with state-of-the-art models and memory systems (32K to 4M tokens) expose a critical weakness: while adept at static retrieval, agents struggle with the dynamic information synthesis essential for workflows. Our analysis indicates that this degradation is driven by the minimum number of tokens required to resolve a query. This factor explains why the high information density inherent in massive tool responses poses a significantly greater challenge than the memory fragmentation typical of long-turn dialogues.

Qi Luo, Xiaonan Li, Yuxin Wang et al.

Large Language Models (LLMs) excel at reasoning and generation but are inherently limited by static pretraining data, resulting in factual inaccuracies and weak adaptability to new information. Retrieval-Augmented Generation (RAG) addresses this issue by grounding LLMs in external knowledge; However, the effectiveness of RAG critically depends on whether the model can adequately access relevant information. Existing RAG systems rely on a single retriever with fixed top-k selection, restricting access to a narrow and static subset of the corpus. As a result, this single-retriever paradigm has become the primary bottleneck for comprehensive external information acquisition, especially in tasks requiring corpus-level reasoning. To overcome this limitation, we propose MARAG-R1, a reinforcement-learned multi-tool RAG framework that enables LLMs to dynamically coordinate multiple retrieval mechanisms for broader and more precise information access. MARAG-R1 equips the model with four retrieval tools -- semantic search, keyword search, filtering, and aggregation -- and learns both how and when to use them through a two-stage training process: supervised fine-tuning followed by reinforcement learning. This design allows the model to interleave reasoning and retrieval, progressively gathering sufficient evidence for corpus-level synthesis. Experiments on GlobalQA, HotpotQA, and 2WikiMultiHopQA demonstrate that MARAG-R1 substantially outperforms strong baselines and achieves new state-of-the-art results in corpus-level reasoning tasks.

Qi Luo, Xiaonan Li, Tingshuo Fan et al.

Retrieval-augmented generation (RAG) has emerged as a leading approach to reducing hallucinations in large language models (LLMs). Current RAG evaluation benchmarks primarily focus on what we call local RAG: retrieving relevant chunks from a small subset of documents to answer queries that require only localized understanding within specific text chunks. However, many real-world applications require a fundamentally different capability -- global RAG -- which involves aggregating and analyzing information across entire document collections to derive corpus-level insights (for example, "What are the top 10 most cited papers in 2023?"). In this paper, we introduce GlobalQA -- the first benchmark specifically designed to evaluate global RAG capabilities, covering four core task types: counting, extremum queries, sorting, and top-k extraction. Through systematic evaluation across different models and baselines, we find that existing RAG methods perform poorly on global tasks, with the strongest baseline achieving only 1.51 F1 score. To address these challenges, we propose GlobalRAG, a multi-tool collaborative framework that preserves structural coherence through chunk-level retrieval, incorporates LLM-driven intelligent filters to eliminate noisy documents, and integrates aggregation modules for precise symbolic computation. On the Qwen2.5-14B model, GlobalRAG achieves 6.63 F1 compared to the strongest baseline's 1.51 F1, validating the effectiveness of our method.

Bowen Li, Haochen Ma, Yuxin Wang et al.

The rapid adoption of Large Language Models (LLMs) has spurred interest in automated peer review; however, progress is currently stifled by benchmarks that treat reviewing primarily as a rating prediction task. We argue that the utility of a review lies in its textual justification--its arguments, questions, and critique--rather than a scalar score. To address this, we introduce Beyond Rating, a holistic evaluation framework that assesses AI reviewers across five dimensions: Content Faithfulness, Argumentative Alignment, Focus Consistency, Question Constructiveness, and AI-Likelihood. Notably, we propose a Max-Recall strategy to accommodate valid expert disagreement and introduce a curated dataset of paper with high-confidence reviews, rigorously filtered to remove procedural noise. Extensive experiments demonstrate that while traditional n-gram metrics fail to reflect human preferences, our proposed text-centric metrics--particularly the recall of weakness arguments--correlate strongly with rating accuracy. These findings establish that aligning AI critique focus with human experts is a prerequisite for reliable automated scoring, offering a robust standard for future research.

Peng Xu, Xinchi Chen, Xiaofei Ma et al.

Recent progress in pretrained Transformer-based language models has shown great success in learning contextual representation of text. However, due to the quadratic self-attention complexity, most of the pretrained Transformers models can only handle relatively short text. It is still a challenge when it comes to modeling very long documents. In this work, we propose to use a graph attention network on top of the available pretrained Transformers model to learn document embeddings. This graph attention network allows us to leverage the high-level semantic structure of the document. In addition, based on our graph document model, we design a simple contrastive learning strategy to pretrain our models on a large amount of unlabeled corpus. Empirically, we demonstrate the effectiveness of our approaches in document classification and document retrieval tasks.

Xinchi Chen, Chunchuan Lyu, Ivan Titov

Semantic role labeling (SRL) involves extracting propositions (i.e. predicates and their typed arguments) from natural language sentences. State-of-the-art SRL models rely on powerful encoders (e.g., LSTMs) and do not model non-local interaction between arguments. We propose a new approach to modeling these interactions while maintaining efficient inference. Specifically, we use Capsule Networks: each proposition is encoded as a tuple of \textit{capsules}, one capsule per argument type (i.e. role). These tuples serve as embeddings of entire propositions. In every network layer, the capsules interact with each other and with representations of words in the sentence. Each iteration results in updated proposition embeddings and updated predictions about the SRL structure. Our model substantially outperforms the non-refinement baseline model on all 7 CoNLL-2019 languages and achieves state-of-the-art results on 5 languages (including English) for dependency SRL. We analyze the types of mistakes corrected by the refinement procedure. For example, each role is typically (but not always) filled with at most one argument. Whereas enforcing this approximate constraint is not useful with the modern SRL system, iterative procedure corrects the mistakes by capturing this intuition in a flexible and context-sensitive way.

Jingjing Gong, Xinchi Chen, Tao Gui et al.

Multi-criteria Chinese word segmentation is a promising but challenging task, which exploits several different segmentation criteria and mines their common underlying knowledge. In this paper, we propose a flexible multi-criteria learning for Chinese word segmentation. Usually, a segmentation criterion could be decomposed into multiple sub-criteria, which are shareable with other segmentation criteria. The process of word segmentation is a routing among these sub-criteria. From this perspective, we present Switch-LSTMs to segment words, which consist of several long short-term memory neural networks (LSTM), and a switcher to automatically switch the routing among these LSTMs. With these auto-switched LSTMs, our model provides a more flexible solution for multi-criteria CWS, which is also easy to transfer the learned knowledge to new criteria. Experiments show that our model obtains significant improvements on eight corpora with heterogeneous segmentation criteria, compared to the previous method and single-criterion learning.

Junkun Chen, Kaiyu Chen, Xinchi Chen et al.

Designing shared neural architecture plays an important role in multi-task learning. The challenge is that finding an optimal sharing scheme heavily relies on the expert knowledge and is not scalable to a large number of diverse tasks. Inspired by the promising work of neural architecture search (NAS), we apply reinforcement learning to automatically find possible shared architecture for multi-task learning. Specifically, we use a controller to select from a set of shareable modules and assemble a task-specific architecture, and repeat the same procedure for other tasks. The controller is trained with reinforcement learning to maximize the expected accuracies for all tasks. We conduct extensive experiments on two types of tasks, text classification and sequence labeling, which demonstrate the benefits of our approach.

Zhan Shi, Xinchi Chen, Xipeng Qiu et al.

Text generation is a crucial task in NLP. Recently, several adversarial generative models have been proposed to improve the exposure bias problem in text generation. Though these models gain great success, they still suffer from the problems of reward sparsity and mode collapse. In order to address these two problems, in this paper, we employ inverse reinforcement learning (IRL) for text generation. Specifically, the IRL framework learns a reward function on training data, and then an optimal policy to maximum the expected total reward. Similar to the adversarial models, the reward and policy function in IRL are optimized alternately. Our method has two advantages: (1) the reward function can produce more dense reward signals. (2) the generation policy, trained by "entropy regularized" policy gradient, encourages to generate more diversified texts. Experiment results demonstrate that our proposed method can generate higher quality texts than the previous methods.

Xinchi Chen, Zhan Shi, Xipeng Qiu et al.

Neural word segmentation has attracted more and more research interests for its ability to alleviate the effort of feature engineering and utilize the external resource by the pre-trained character or word embeddings. In this paper, we propose a new neural model to incorporate the word-level information for Chinese word segmentation. Unlike the previous word-based models, our model still adopts the framework of character-based sequence labeling, which has advantages on both effectiveness and efficiency at the inference stage. To utilize the word-level information, we also propose a new long short-term memory (LSTM) architecture over directed acyclic graph (DAG). Experimental results demonstrate that our model leads to better performances than the baseline models.

Xinchi Chen, Zhan Shi, Xipeng Qiu et al.

Different linguistic perspectives causes many diverse segmentation criteria for Chinese word segmentation (CWS). Most existing methods focus on improve the performance for each single criterion. However, it is interesting to exploit these different criteria and mining their common underlying knowledge. In this paper, we propose adversarial multi-criteria learning for CWS by integrating shared knowledge from multiple heterogeneous segmentation criteria. Experiments on eight corpora with heterogeneous segmentation criteria show that the performance of each corpus obtains a significant improvement, compared to single-criterion learning. Source codes of this paper are available on Github.

Xinchi Chen, Xipeng Qiu, Xuanjing Huang

Recently, neural network models for natural language processing tasks have been increasingly focused on for their ability of alleviating the burden of manual feature engineering. However, the previous neural models cannot extract the complicated feature compositions as the traditional methods with discrete features. In this work, we propose a feature-enriched neural model for joint Chinese word segmentation and part-of-speech tagging task. Specifically, to simulate the feature templates of traditional discrete feature based models, we use different filters to model the complex compositional features with convolutional and pooling layer, and then utilize long distance dependency information with recurrent layer. Experimental results on five different datasets show the effectiveness of our proposed model.

Jingjing Gong, Xinchi Chen, Xipeng Qiu et al.

Sentence ordering is one of important tasks in NLP. Previous works mainly focused on improving its performance by using pair-wise strategy. However, it is nontrivial for pair-wise models to incorporate the contextual sentence information. In addition, error prorogation could be introduced by using the pipeline strategy in pair-wise models. In this paper, we propose an end-to-end neural approach to address the sentence ordering problem, which uses the pointer network (Ptr-Net) to alleviate the error propagation problem and utilize the whole contextual information. Experimental results show the effectiveness of the proposed model. Source codes and dataset of this paper are available.

Xinchi Chen, Xipeng Qiu, Xuanjing Huang

Sentence ordering is a general and critical task for natural language generation applications. Previous works have focused on improving its performance in an external, downstream task, such as multi-document summarization. Given its importance, we propose to study it as an isolated task. We collect a large corpus of academic texts, and derive a data driven approach to learn pairwise ordering of sentences, and validate the efficacy with extensive experiments. Source codes and dataset of this paper will be made publicly available.

Xinchi Chen, Xipeng Qiu, Jingxiang Jiang et al.

Recently, word representation has been increasingly focused on for its excellent properties in representing the word semantics. Previous works mainly suffer from the problem of polysemy phenomenon. To address this problem, most of previous models represent words as multiple distributed vectors. However, it cannot reflect the rich relations between words by representing words as points in the embedded space. In this paper, we propose the Gaussian mixture skip-gram (GMSG) model to learn the Gaussian mixture embeddings for words based on skip-gram framework. Each word can be regarded as a gaussian mixture distribution in the embedded space, and each gaussian component represents a word sense. Since the number of senses varies from word to word, we further propose the Dynamic GMSG (D-GMSG) model by adaptively increasing the sense number of words during training. Experiments on four benchmarks show the effectiveness of our proposed model.

Chenxi Zhu, Xipeng Qiu, Xinchi Chen et al.

In this work, we address the problem to model all the nodes (words or phrases) in a dependency tree with the dense representations. We propose a recursive convolutional neural network (RCNN) architecture to capture syntactic and compositional-semantic representations of phrases and words in a dependency tree. Different with the original recursive neural network, we introduce the convolution and pooling layers, which can model a variety of compositions by the feature maps and choose the most informative compositions by the pooling layers. Based on RCNN, we use a discriminative model to re-rank a $k$-best list of candidate dependency parsing trees. The experiments show that RCNN is very effective to improve the state-of-the-art dependency parsing on both English and Chinese datasets.