DeepWeaver: Bridging the Evidence Synthesis Gap in Open-Ended Question Answering

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. Our code is available at https://github.com/KlozeWang/DeepWeaver.

SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization

Sparse autoencoders (SAEs) are proposed to extract numerous features from large language model (LLM) representations, yet explaining these features still relies primarily on external observation. This reliance leads to superficial explanations inferred from observed model behavior and computational inefficiency from collecting such behavioral evidence at scale. We introduce SAEVerbalizer, a framework that injects SAE decoder directions into an LLM's representations and fine-tunes the LLM's downstream layers to generate natural-language explanations of the injected features. Once trained, the resulting verbalizer explains SAE features directly from decoder directions, addressing both limitations. Our experiments show that the learned verbalization capability generalizes to unseen features, transfers across separately trained SAE dictionaries, and, with a lightweight adapter, extends to SAE features from different LLMs. Intervention experiments show that injecting multiple directions yields an explanation combining their meanings, while reversing individual directions produces corresponding meaning shifts.

SurveyReview: A Reviewer-Aligned Benchmark for Survey Evaluators

The rapid advancement of large language models has transformed survey writing from a months-long manual effort into an automated process. As generation scales, reliable evaluation becomes the bottleneck, and LLMs are increasingly used as survey evaluators. However, existing approaches largely rely on off-the-shelf LLM-as-a-judge methods without systematic alignment to human reviewers, and there remains a lack of systematic frameworks for quantifying alignment with human reviewers. To address this gap, we propose SurveyReview, a reviewer-aligned, multi-dimensional benchmark and dataset for survey evaluation. We collect and annotate 675 survey papers with 1,630 review reports. We structure authentic peer-review reports by converting free-form comments into four-dimensional scores (Readability, Criticalness, Comprehensiveness, Structure) paired with supporting rationales. We further release standardized train/test splits and an evaluation protocol to measure alignment between automatic evaluators and human reviewers. To validate the benchmark, we develop SurveyAlign, a strong baseline evaluator by fine-tuning Qwen3-32B with LoRA on our annotated data, augmented with external knowledge for knowledge-intensive dimensions. On the test set, SurveyAlign substantially improves reviewer alignment over prompt-based judging with GPT-5.2, reducing average MSE from 2.28 to 1.38 and MAE from 1.15 to 0.69 across all four dimensions. Our contributions are twofold: (1) we establish the first multi-dimensional, reviewer-aligned dataset with a reproducible evaluation framework for survey reviewing; (2) we develop a strong baseline evaluator that substantially improves alignment with human reviewers, providing a competitive reference for future research. Our code and data are available at https://surveyreview.github.io

TRAJDEBUG: Tracing Error Lifecycle to Identify Critical Failures in Long-Horizon Agent Trajectories

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 Tau2Bench 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.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs

Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) exhibit fundamentally different behaviors in enhancing multi-task reasoning for large language models (LLMs). Our preliminary experiments revealed a phenomenon: SFT suffers from severe task conflicts under multi-stage training, whereas RL enables stable coexistence across diverse tasks. Empirically, we trace this to the parameter level, observing that RL induces sparse and approximately orthogonal updates across tasks. We provide a theoretical explanation for this mechanism by analyzing multi-task gradient interference. Our results reveal a distinction: interference in SFT is norm-limited, scaling with the absolute gradient magnitude, whereas interference in RL is variance-limited, bounded by the gradient variance induced by advantage normalization and on-policy optimization. This small variance bound yields near-orthogonal optimization directions across tasks. Leveraging this insight, we propose Parallel-RL, a paradigm that decouples multi-task training, significantly improving efficiency and flexibility.

Where Steering Signals Come From: Activation Source Selection in Activation Steering

Activation steering controls language models by adding vectors or features to hidden states at inference time, but the upstream source of these steering signals is often treated as a secondary detail. We study this source choice as activation source selection: the combination of source context and activation readout policy used to collect the hidden states from which a steering signal is built. Holding the downstream intervention fixed, we show across three instruction-tuned models and four steering task families that changing only the source activations substantially changes steering success. We further find that effective steering is not explained simply by whether the desired behavior appears in the source text. Instead, strong signals come from execution-boundary states, where the model is about to produce or continue the target behavior. This pre-/post-realization distinction explains why answer-based sources sometimes work: their useful component aligns with execution-boundary directions rather than target appearance alone. Building on this view, we introduce tail subtraction, which removes shared prompt and continuation semantics from boundary states and yields cleaner, more stable steering signals. Overall, our results suggest that steering depends on representations of what the model is about to do, not merely on what has already appeared.

Can LLM-as-a-Judge Reliably Verify Rubrics in Agentic Scenarios?

Rubric-based scoring has become a widely used paradigm in model evaluation, typically with LLM-as-a-Judge (LaaJ) for rubric scoring. However, the reliability of LaaJ for rubric scoring remains underexplored. This concern is especially pronounced in agentic scenarios, where long, complex outputs further challenge reliable scoring. To address this, we conduct a systematic meta-evaluation of LaaJ reliability for rubric verification. We introduce RuVerBench, the first benchmark for assessing LaaJ reliability in rubric verification for agentic scenarios. RuVerBench covers two prevalent agentic domains, deep research and agentic coding, with 2,458 instances, each containing a model-generated output, a rubric, and a human-annotated label indicating whether the output satisfies the rubric. Using RuVerBench, we evaluate numerous frontier LLMs and find that even the most advanced models achieve strong performance but still exhibit substantial noise. We further analyze the impact of key LaaJ strategies, including prompt design, batching, and majority voting, on rubric verification. We find that weaker models are more sensitive to prompt variations, batched verification presents a trade-off between accuracy and efficiency, and majority voting yields effective but diminishing returns. We have released our dataset and code to facilitate future research: https://github.com/THU-KEG/RuVerBench.

HG-Bench: A Benchmark for Multi-Page Handwritten Answer-Region Grounding in Automated Homework Assessment

Automated homework assessment depends not only on recognizing student answers, but also on accurately locating where each answer and each intermediate reasoning step appears in noisy, multi-page handwritten work. This paper addresses the missing evaluation setting of page-aware, two-level answer-region grounding: given a sequence of homework page images, a model must localize complete answer regions and their ordered step-level subregions. We introduce HG-Bench, a benchmark of 500 human-annotated K-12 homework samples curated from a 1,489,278-image source pool, with question-level and step-level boxes linked by a hierarchical containment constraint. HG-Bench is paired with a page-aware evaluation protocol that separately measures complete-answer localization (FA) and step-level decomposition (FSm), revealing whether models truly ground the spatial structure of student reasoning rather than merely parse visible text. Across frontier closed-source APIs and competitive open-weight VLMs, no zero-shot system exceeds 55.22% on FA or 48.22% on FSm, while a GLM-4.6V 9B reference model fine-tuned on ~10k in-domain examples reaches 74.97/72.26. These results identify step-level handwritten grounding as a concrete capability gap and provide a reproducible benchmark, evaluation protocol, and trained reference point for future work on automated homework assessment.

An LMM for Precisely Grounding Elements in Documents

Visual grounding in documents is a crucial ability for Large Multimodal Models (LMMs) in areas such as document understanding, deep research and document error detection. However, existing approaches exhibit poor grounding precision in text-rich document images, often failing to accurately locate the critical document elements needed for reliable reasoning. To address this gap, we introduce PreciseDoc, an LMM specifically designed for precise element grounding and can be further optimized for Document VQA tasks. Specifically, to enhance the basic localization capability, we construct challenging training data by two pipelines capable of mass-producing high-quality documents with paired metadata of fine-grained coordinates, including synthetic hand-filled documents with camera effects. The model develops more real-world functions beyond straightforward localization of single text, such as locating personal information from CVs. Furthermore, we introduce a training paradigm for visual grounded reasoning where the grounding and reasoning are supervised jointly with reinforcement learning to improve the contribution of the grounded evidence. A comprehensive evaluation on various benchmarks demonstrates the advantage of the proposed data and methods in document spatial grounding and document understanding.

EnvRL: Learn from Environment Dynamics in Agentic Reinforcement Learning

Reinforcement learning (RL) has emerged as a powerful paradigm for training Large Language Models (LLMs) as agents. However, conventional RL methods for long-horizon agentic tasks often struggle with sparse outcome rewards. Intuitively, this overlooks the rich environment dynamics information contained in rollout interaction trajectories. We argue that the interaction experience inherently serves as an implicit supervision signal, reveals the underlying transition mechanisms of the environment, and enables the agent to construct a more accurate internal model of the environment.. Therefore, in this work, we investigate how to leverage this additional signal to improve policy learning. Specifically, we propose EnvRL, a framework that incorporates environment dynamics learning into agentic RL via two auxiliary objectives: state prediction and inverse dynamics. By jointly optimizing with the primary RL objective, we encourage the agent to internalize environment dynamics from its own interaction experience. Extensive experiments on two long-horizon agentic benchmarks demonstrate that EnvRL achieves significant improvements on success-rates over RL-only baselines, e.g., when trained with GRPO, lifting Qwen-2.5-1.5B-Instruct from 72.8% to 77.4% on ALFWorld, and from 56.8% to 67.0% on WebShop.