Knowledge Graphs (KGs) structure real-world entities and their relationships into triples, enhancing machine reasoning for various tasks. While domain-specific KGs offer substantial benefits, their manual construction is often inefficient and requires specialized knowledge. Recent approaches for knowledge graph construction (KGC) based on large language models (LLMs), such as schema-guided KGC and reference knowledge integration, have proven efficient. However, these methods are constrained by their reliance on manually defined schema, single-document processing, and public-domain references, making them less effective for domain-specific corpora that exhibit complex knowledge dependencies and specificity, as well as limited reference knowledge. To address these challenges, we propose LKD-KGC, a novel framework for unsupervised domain-specific KG construction. LKD-KGC autonomously analyzes document repositories to infer knowledge dependencies, determines optimal processing sequences via LLM driven prioritization, and autoregressively generates entity schema by integrating hierarchical inter-document contexts. This schema guides the unsupervised extraction of entities and relationships, eliminating reliance on predefined structures or external knowledge. Extensive experiments show that compared with state-of-the-art baselines, LKD-KGC generally achieves improvements of 10% to 20% in both precision and recall rate, demonstrating its potential in constructing high-quality domain-specific KGs.

Developing autonomous agents capable of mastering complex, multi-step tasks in unpredictable, interactive environments presents a significant challenge. While Large Language Models (LLMs) offer promise for planning, existing approaches often rely on problematic internal knowledge or make unrealistic environmental assumptions. Although recent work explores learning planning knowledge, they still retain limitations due to partial reliance on external knowledge or impractical setups. Indeed, prior research has largely overlooked developing agents capable of acquiring planning knowledge from scratch, directly in realistic settings. While realizing this capability is necessary, it presents significant challenges, primarily achieving robustness given the substantial risk of incorporating LLMs' inaccurate knowledge. Moreover, efficiency is crucial for practicality as learning can demand prohibitive exploration. In response, we introduce Robust and Efficient Planning for Open-world Agents (REPOA), a novel framework designed to tackle these issues. REPOA features three key components: adaptive dependency learning and fine-grained failure-aware operation memory to enhance robustness to knowledge inaccuracies, and difficulty-based exploration to improve learning efficiency. Our evaluation in two established open-world testbeds demonstrates REPOA's robust and efficient planning, showcasing its capability to successfully obtain challenging late-game items that were beyond the reach of prior approaches.

Training language models with rationales augmentation has been shown to be beneficial in many existing works. In this paper, we identify that such a prevailing view does not hold consistently. We conduct comprehensive investigations to thoroughly inspect the impact of rationales on model performance as well as a novel perspective of model reliability. The results lead to several key findings that add new insights upon existing understandings: 1) Rationales can, at times, deteriorate model performance; 2) Rationales can, at times, improve model reliability, even outperforming their untrained counterparts; 3) A linear correspondence exists in between the performance and reliability improvements, while both are driven by the intrinsic difficulty of the task. These findings provide informative regulations on the broad utilization of rationales and raise critical implications on the procedure of explicitly aligning language models with implicit human thoughts. Codes can be found at https://github.com/Ignoramus0817/rationales.

In-Context Learning (ICL) enhances the performance of large language models (LLMs) with demonstrations. However, obtaining these demonstrations primarily relies on manual effort. In most real-world scenarios, users are often unwilling or unable to provide such demonstrations. Inspired by the human analogy, we explore a new ICL paradigm CrossICL to study how to utilize existing source task demonstrations in the ICL for target tasks, thereby obtaining reliable guidance without any additional manual effort. To explore this, we first design a two-stage alignment strategy to mitigate the interference caused by gaps across tasks, as the foundation for our experimental exploration. Based on it, we conduct comprehensive exploration of CrossICL, with 875 NLP tasks from the Super-NI benchmark and six types of LLMs, including GPT-4o. Experimental results demonstrate the effectiveness of CrossICL and provide valuable insights on questions like the criteria for selecting cross-task demonstrations, as well as the types of task-gap-induced interference in CrossICL.

We present EHRMIND, a practical recipe for adapting large language models (LLMs) to complex clinical reasoning tasks using reinforcement learning with verifiable rewards (RLVR). While RLVR has succeeded in mathematics and coding, its application to healthcare contexts presents unique challenges due to the specialized knowledge and reasoning required for electronic health record (EHR) interpretation. Our pilot study on the MEDCALC benchmark reveals two key failure modes: (1) misapplied knowledge, where models possess relevant medical knowledge but apply it incorrectly, and (2) missing knowledge, where models lack essential domain knowledge. To address these cases, EHRMIND applies a two-stage solution: a lightweight supervised fine-tuning (SFT) warm-up that injects missing domain knowledge, stabilizes subsequent training, and encourages structured, interpretable outputs; followed by RLVR, which reinforces outcome correctness and refines the model's decision-making. We demonstrate the effectiveness of our method across diverse clinical applications, including medical calculations (MEDCALC), patient-trial matching (TREC CLINICAL TRIALS), and disease diagnosis (EHRSHOT). EHRMIND delivers consistent gains in accuracy, interpretability, and cross-task generalization. These findings offer practical guidance for applying RLVR to enhance LLM capabilities in healthcare settings.

Verifiers play a crucial role in large language model (LLM) reasoning, needed by post-training techniques such as reinforcement learning. However, reliable verifiers are hard to get for difficult coding problems, because a well-disguised wrong solution may only be detected by carefully human-written edge cases that are difficult to synthesize. To address this issue, we propose HARDTESTGEN, a pipeline for high-quality test synthesis using LLMs. With this pipeline, we curate a comprehensive competitive programming dataset HARDTESTS with 47k problems and synthetic high-quality tests. Compared with existing tests, HARDTESTGEN tests demonstrate precision that is 11.3 percentage points higher and recall that is 17.5 percentage points higher when evaluating LLM-generated code. For harder problems, the improvement in precision can be as large as 40 points. HARDTESTS also proves to be more effective for model training, measured by downstream code generation performance. We will open-source our dataset and synthesis pipeline at https://leililab.github.io/HardTests/.

Large Language Models (LLMs) have demonstrated remarkable performance on various medical question-answering (QA) benchmarks, including standardized medical exams. However, correct answers alone do not ensure correct logic, and models may reach accurate conclusions through flawed processes. In this study, we introduce the MedPAIR (Medical Dataset Comparing Physicians and AI Relevance Estimation and Question Answering) dataset to evaluate how physician trainees and LLMs prioritize relevant information when answering QA questions. We obtain annotations on 1,300 QA pairs from 36 physician trainees, labeling each sentence within the question components for relevance. We compare these relevance estimates to those for LLMs, and further evaluate the impact of these "relevant" subsets on downstream task performance for both physician trainees and LLMs. We find that LLMs are frequently not aligned with the content relevance estimates of physician trainees. After filtering out physician trainee-labeled irrelevant sentences, accuracy improves for both the trainees and the LLMs. All LLM and physician trainee-labeled data are available at: http://medpair.csail.mit.edu/.

Large language models (LLMs) have achieved remarkable success across various tasks but face deployment challenges due to their massive computational demands. While post-training pruning methods like SparseGPT and Wanda can effectively reduce the model size, but struggle to maintain model performance at high sparsity levels, limiting their utility for downstream tasks. Existing fine-tuning methods, such as full fine-tuning and LoRA, fail to preserve sparsity as they require updating the whole dense metrics, not well-suited for sparse LLMs. In this paper, we propose Sparsity Evolution Fine-Tuning (SEFT), a novel method designed specifically for sparse LLMs. SEFT dynamically evolves the sparse topology of pruned models during fine-tuning, while preserving the overall sparsity throughout the process. The strengths of SEFT lie in its ability to perform task-specific adaptation through a weight drop-and-grow strategy, enabling the pruned model to self-adapt its sparse connectivity pattern based on the target dataset. Furthermore, a sensitivity-driven pruning criterion is employed to ensure that the desired sparsity level is consistently maintained throughout fine-tuning. Our experiments on various LLMs, including LLaMA families, DeepSeek, and Mistral, across a diverse set of benchmarks demonstrate that SEFT achieves stronger performance while offering superior memory and time efficiency compared to existing baselines. Our code is publicly available at: https://github.com/QiaoXiao7282/SEFT.

Knowledge graph completion aims to address the gaps of knowledge bases by adding new triples that represent facts. The complexity of this task depends on how many parts of a triple are already known. Instance completion involves predicting the relation-tail pair when only the head is given (h, ?, ?). Notably, modern knowledge bases often contain entity descriptions and types, which can provide valuable context for inferring missing facts. By leveraging these textual descriptions and the ability of large language models to extract facts from them and recognize patterns within the knowledge graph schema, we propose an LLM-powered, end-to-end instance completion approach. Specifically, we introduce GenIC: a two-step Generative Instance Completion framework. The first step focuses on property prediction, treated as a multi-label classification task. The second step is link prediction, framed as a generative sequence-to-sequence task. Experimental results on three datasets show that our method outperforms existing baselines. Our code is available at https://github.com/amal-gader/genic.

We investigate whether hidden states from Structured State Space Models (SSMs) can be merged post-hoc to support downstream reasoning. Inspired by model souping, we propose a strategy where documents are encoded independently and their representations are pooled -- via simple operations like averaging -- into a single context state. This approach, which we call document souping, enables modular encoding and reuse without reprocessing the full input for each query. We finetune Mamba2 models to produce soupable representations and find that they support multi-hop QA, sparse retrieval, and long-document reasoning with strong accuracy. On HotpotQA, souping ten independently encoded documents nearly matches the performance of a cross-encoder trained on the same inputs.