Retrieve-then-generate pipelines are commonly used to produce deep-research answers for open-ended questions, but retrieval alone is insufficient: LLMs must organize noisy and fragmented evidence into comprehensive, well-cited answers. We refer to this process as **evidence synthesis**. However, direct generation often underuses evidence, misaligns citations, and collapses diverse information into shallow summaries, exposing an evidence synthesis gap between retrieval and generation. Thus, we propose **DeepWeaver**, a novel framework that weaves noisy retrieved evidence into comprehensive answers by maintaining Thought Block Chains (TBCs), a structured representation that groups claims, salient information, keywords, and supporting evidence. DeepWeaver uses subordinate TBCs to inspect residual evidence, commit TBC revisions, and discover new claims before final generation. We evaluate DeepWeaver on open-ended QA over both knowledge bases and the web, and introduce **LoQA**, a high-density benchmark for evidence synthesis. Across multiple LLMs, DeepWeaver improves content sufficiency, citation grounding, and detail preservation on LoQA, while achieving deeper insights and higher citation quality on DeepResearch Bench. These results show that evidence weaving is an effective mechanism for bridging retrieval and generation in open-ended QA.

Large language model (LLM) personalization aims to generate responses that align with individual user preferences, making accurate preference inference critical. In practice, user-LLM interaction histories naturally contain rich preference signals. However, extracting preferences from these histories remains underexplored and challenging: the history can be long and noisy, preferences may evolve over time, and preferences may vary across situations even within the same topic. To address these challenges, we develop PREFINFER, a model that accurately infers user preferences from the user’s interaction history with an LLM. Specifically, we introduce PREFMINE, an automated data construction method that synthesizes high-quality preference inference data, where each sample includes a synthetic interaction history, a current user request, and the user’s preference for the current request, and construct PREFMINE-15K for training PREFINFER. Experiments show that PREFINFER achieves advanced performance on preference inference, and the preferences inferred by PREFINFER effectively guide LLMs to generate responses better aligned with user preferences. We conduct thorough ablation studies on the key design choices of PREFMINE, validating their effectiveness. We have released the code, data, and models to facilitate further research(https://github.com/THU-KEG/PREFINFER).

LLM-based agentic systems have shown remarkable capabilities in complex domains, while suffering from cascading errors and difficulty in debugging. Critical error detection aims to locate the earliest error step in a failed trajectory that is responsible for the final failure. However, progress faces two main challenges. First, long trajectories make it difficult to identify individual errors, since the evidence for judging a step may be scattered across distant instructions, observations, and prior context. Second, failed trajectories often contain multiple local errors with different downstream effects, only some of which remain responsible for the final failure. In this work, we propose TrajDebug, an error-lifecycle tracing framework that addresses long-trajectory error discovery with multi-granularity history compression and evidence-based error identification, and supports critical attribution by tracing each error’s resolution status and terminal impact. We further construct TrajErrBench, a benchmark of 486 manually annotated failed trajectories from and SWE-Bench Pro, covering realistic tool-use and coding scenarios. Experiments across diverse agent benchmarks show that TrajDebug achieves the best overall performance over existing baselines, and application studies further demonstrate that its diagnoses provide actionable feedback for improving downstream agent success. We will release the codes and data to facilitate further research.

UI videos provide a natural input for generating interactive webpages, as they capture both webpage appearance and action-triggered state transitions. However, directly applying video-capable vision-language models to this task remains insufficient. Existing models typically rely on sparse sampling or compressed temporal representations, which may miss short action boundaries and break the state-action-state transitions needed to implement webpage behavior. We formulate UI video-to-code generation as executable state-transition recovery from interaction videos, and identify this failure mode as state-transition misalignment. We introduce Video2Code, an action-aware video-to-code approach for recovering executable UI state transitions. Rather than allocating the visual budget uniformly across the video, Video2Code first performs coarse video understanding to locate action-critical regions, then invokes a temporal clipping tool to revisit these regions at higher temporal resolution before generating HTML/CSS/JavaScript code. We instantiate Video2Code with action-aligned video-code supervision and evaluate it under both visual and functional criteria. Experiments show that Video2Code substantially strengthens the underlying open-source model for UI video-to-code generation, improving functional correctness over direct video observation, especially on dense multi-step interactions. Our code is available at https://github.com/kiwixu1024/Video2code.

Project-Based Learning (PBL) is an important learning method that promotes understanding and acquiring practical skills through training learners through a project. However, effective PBL often requires sustained orchestration and collaboration, but existing LLM-based learning tools provide partial assistance without explicitly modeling these roles, and overly comprehensive help provided by LLM can reduce learner autonomy. We propose SimPBL, a multi-agent framework with an orchestrator agent that provides adaptive scaffolding from interaction logs and collaborator agents that support project work through boundary-aware collaboration. We conduct comprehensive evaluation to study the effectiveness of SimPBL, where we observe a 14% improvement in learner examination score. Results from extensive studies further highlights the ability of SimPBL to manage learning behavior and improve learning experience. Code and materials are available at https://anonymous.4open.science/r/SimPBL-D5B8.

Knowing and teaching differ fundamentally: effective instruction requires transforming knowledge into forms learners can grasp. Large language models, when asked to generate lessons (a concrete form of teaching), produce content lacking pedagogical depth. We trace this failure to three decisions that expert teachers make: selecting content by recognizing each source’s instructional role, sequencing topics so foundations precede applications, and synthesizing components into a unified whole. To scaffold these decisions, we introduce TeachCraft, a framework with three agents: Explorer classifies sources by pedagogical intent to guide selection; Planner orders objectives from foundational to advanced; Generator produces lesson materials through a schema that ensures consistency across components. To evaluate this approach, we construct LessonBench, 40 expert-designed lessons paired with two to five heterogeneous source documents, on which TeachCraft achieves 67.8% win rate in human evaluation and 79.6% in LLM-based evaluation against eight baselines, with ablations confirming that each decision contributes independently to overall lesson quality.[Source code is available at https://anonymous.4open.science/r/TeachCraft-1672]

Parameter-Efficient Fine-Tuning (PEFT) methods, such as LoRA, significantly reduce the number of trainable parameters by introducing low-rank decomposition matrices. However, existing methods perform extensive matrix multiplications in domain specialization tasks, resulting in computational inefficiency and sub-optimal fine-tuning performance. Hence, we propose LoSiA (Low-Resources Subnet Integration Adaptation), an innovative method that dynamically localizes and optimizes critical parameters during the training process. Specifically, it identifies a sub-network using gradient sparsity analysis and optimizes it as the trainable target. This design enables effective high-rank adaptation by updating only the sub-network parameters, reducing the additional matrix multiplication. We also present LoSiA-Pro, a faster implementation of LoSiA, which reduces the training latency by about 27% compared to LoRA. Extensive evaluations show that our method achieves minimal performance drop compared to full fine-tuning, while requiring the least training time across domain specialization and common-sense reasoning tasks. Further analysis shows that LoSiA also reduces forgetting during continued training.

Reinforcement learning with verifiable rewards (RLVR) has become a key technique for enhancing large language models (LLMs), with verification engineering playing a central role. However, best practices for RL in instruction following remain underexplored. In this work, we explore the verification challenge in RL for instruction following and propose VerIF, a verification method that combines rule-based code verification with LLM-based verification from a large reasoning model (e.g., QwQ-32B). To support this approach, we construct a high-quality instruction-following dataset, VerInstruct, containing approximately 22,000 instances with associated verification signals. We apply RL training with VerIF to two models, achieving significant improvements across several representative instruction-following benchmarks. The trained models reach state-of-the-art performance among models of comparable size and generalize well to unseen constraints. We further observe that their general capabilities remain unaffected, suggesting that RL with VerIF can be integrated into existing RL recipes to enhance overall model performance. We will release our datasets, codes, and models to facilitate future research.

Reward models (RMs) are crucial for the training and inference-time scaling up of large language models (LLMs). However, existing reward models primarily focus on human preferences, neglecting verifiable correctness signals which have shown strong potential in training LLMs. In this paper, we propose agentic reward modeling, a reward system that combines reward models with verifiable correctness signals from different aspects to provide reliable rewards. We empirically implement a reward agent, named RewardAgent, that combines human preference rewards with two verifiable signals: factuality and instruction following, to provide more reliable rewards. We conduct comprehensive experiments on existing reward model benchmarks and inference-time best-of-n searches on real-world downstream tasks. RewardAgent significantly outperforms vanilla reward models, demonstrating its effectiveness. We further construct training preference pairs using RewardAgent and train an LLM with the DPO objective, achieving superior performance on various NLP benchmarks compared to conventional reward models. Our codes are publicly released to facilitate further research.

Event Factuality Detection (EFD) task determines the factuality of textual events, i.e., classifying whether an event is a fact, possibility, or impossibility, which is essential for faithfully understanding and utilizing event knowledge. However, due to the lack of high-quality large-scale data, event factuality detection is under-explored in event understanding research, which limits the development of EFD community. To address these issues and provide faithful event understanding, we introduce MAVEN-FACT, a large-scale and high-quality EFD dataset based on the MAVEN dataset. MAVEN-FACT includes factuality annotations of 112,276 events, making it the largest EFD dataset. Extensive experiments demonstrate that MAVEN-FACT is challenging for both conventional fine-tuned models and large language models (LLMs). Thanks to the comprehensive annotations of event arguments and relations in MAVEN, MAVEN-FACT also supports some further analyses and we find that adopting event arguments and relations helps in event factuality detection for fine-tuned models but does not benefit LLMs. Furthermore, we preliminarily study an application case of event factuality detection and find it helps in mitigating event-related hallucination in LLMs. We will release our dataset and codes to facilitate further research on event factuality detection.

Event extraction aims to identify events and then extract the arguments involved in those events. In recent years, there has been a gradual shift from sentence-level event extraction to document-level event extraction research. Despite the significant success achieved in English domain event extraction research, event extraction in Chinese still remains largely unexplored. However, a major obstacle to promoting Chinese document-level event extraction is the lack of fine-grained, wide domain coverage datasets for model training and evaluation. In this paper, we propose DocEE-zh, a new Chinese document-level event extraction dataset comprising over 36,000 events and more than 210,000 arguments. DocEE-zh is an extension of the DocEE dataset, utilizing the same event schema, and all data has been meticulously annotated by human experts. We highlight two features: focus on high-interest event types and fine-grained argument types. Experimental results indicate that state-of-the-art models still fail to achieve satisfactory performance, with an F1 score of 45.88% on the event argument extraction task, revealing that Chinese document-level event extraction (DocEE) remains an unresolved challenge. DocEE-zh is now available at https://github.com/tongmeihan1995/DocEE.git.

Semi-structured interviews are a crucial method of data acquisition in qualitative research. Typically controlled by the interviewer, the process progresses through a question-and-answer format, aimed at eliciting information from the interviewee. However, interviews are highly time-consuming and demand considerable experience of the interviewers, which greatly limits the efficiency and feasibility of data collection. Therefore, we introduce LM-Interview, a novel system designed to automate the process of preparing, conducting and analyzing semi-structured interviews. Experimental results demonstrate that LM-interview achieves performance comparable to that of skilled human interviewers.

Event extraction aims to identify an event and then extract the arguments participating in the event. Despite the great success in sentence-level event extraction, events are more naturally presented in the form of documents, with event arguments scattered in multiple sentences. However, a major barrier to promote document-level event extraction has been the lack of large-scale and practical training and evaluation datasets. In this paper, we present DocEE, a new document-level event extraction dataset including 27,000+ events, 180,000+ arguments. We highlight three features: large-scale manual annotations, fine-grained argument types and application-oriented settings. Experiments show that there is still a big gap between state-of-the-art models and human beings (41% Vs 85% in F1 score), indicating that DocEE is an open issue. DocEE is now available at https://github.com/tongmeihan1995/DocEE.git.