Long Chain-of-Thought (LCoT), achieved by Reinforcement Learning with Verifiable Rewards (RLVR), has proven effective in enhancing the reasoning capabilities of Large Language Models (LLMs). However, reasoning in current LLMs is primarily generated as plain text, where performing semantic evaluation on such unstructured data creates a computational bottleneck during training. Despite RLVR-based optimization, existing methods still suffer from coarse-grained supervision, reward hacking, high training costs, and poor generalization.To address these issues, we propose the Graph Reasoning Paradigm (GRP), which realizes structured and symbolic reasoning, implemented via graph-structured representations with step-level cognitive labels. Building upon GRP, we further design Process-Aware Stratified Clipping Group Relative Policy Optimization (PASC-GRPO), which leverages structured evaluation to replace semantic evaluation, achieves process-aware verification through graph-structured outcome rewards, and mitigates reward hacking via stratified clipping advantage estimation. Experiments demonstrate significant improvements across mathematical reasoning and code generation tasks. Data, models, and code will be released later.

Supervised fine-tuning (SFT) on chain-of-thought (CoT) trajectories demonstrations is a common approach for enabling reasoning in large language models. Standard practices typically only retain trajectories with correct final answers (positives) while ignoring the rest (negatives). We argue that this paradigm discards substantial supervision and exacerbates overfitting, limiting out-of-domain (OOD) generalization. Specifically, we surprisingly find that incorporating negative trajectories into SFT yields substantial OOD generalization gains over positive-only training, as these trajectories often retain valid intermediate reasoning despite incorrect final answers. To understand this effect in depth, we systematically analyze data, training dynamics, and inference behavior, identifying 22 recurring patterns in negative chains that serve a dual role: they moderate loss descent to mitigate overfitting during training and boost policy entropy by 35.67% during inference to facilitate exploration. Motivated by these observations, we further propose Gain-based LOss Weighting (GLOW), an adaptive, sample-aware scheme that exploits such distinctive training dynamics by rescaling per-sample loss based on inter-epoch progress. Empirically, GLOW efficiently leverages unfiltered trajectories, yielding a 5.51% OOD gain over positive-only SFT on Qwen2.5-7B and boosting MMLU from 72.82% to 76.47% as an RL initialization. Code is available at Github.

The release of OpenAI’s O1 and subsequent projects like DeepSeek R1 has significantly advanced research on complex reasoning in LLMs. This paper systematically analyzes existing reasoning studies from the perspective of self-evolution, structured into three components: data evolution, model evolution, and self-evolution. Data evolution explores methods to generate higher-quality reasoning training data. Model evolution focuses on training strategies to boost reasoning capabilities. Self-evolution research autonomous system evolution via iterating cycles of data and model evolution. We further discuss the scaling law of self-evolution and analyze representative O1-like works through this lens. By summarizing advanced methods and outlining future directions, this paper aims to drive advancements in LLMs’ reasoning abilities.

Although large language models (LLMs) have demonstrated remarkable reasoning capabilities, they still face challenges in knowledge-intensive multi-hop reasoning. Recent work explores iterative retrieval to address complex problems. However, the absence of intermediate guidance often leads to inaccurate retrieval and intermediate reasoning errors, leading to incorrect reasoning. To address these, we propose Self-Critique Guided Iterative Reasoning (SiGIR), which uses self-critique feedback to guide the iterative reasoning process. Specifically, through end-to-end training, we enable the model to iteratively address complex problems via question decomposition, while also being able to self-evaluate its intermediate reasoning steps. During iterative reasoning, the model engages in branching exploration and employs self-evaluation to guide the selection of promising reasoning trajectories. Extensive experiments on three multi-hop reasoning datasets demonstrate the effectiveness of our proposed method, surpassing the previous SOTA by 8.6%. Furthermore, our thorough analysis offers insights for future research. Our code, data, and models are available at https://github.com/zchuz/SiGIR-MHQA.

Large Multimodal Models (LMMs) have recently demonstrated impressive performance on general video comprehension benchmarks. Nevertheless, for broader applications, the robustness of their temporal analysis capability needs to be thoroughly investigated yet predominantly ignored. Motivated by this, we propose a novel temporal robustness benchmark (TemRobBench), which introduces temporal inconsistency perturbations separately at the visual and textual modalities to assess the robustness of models. We evaluate 16 mainstream LMMs and find that they exhibit over-reliance on prior knowledge and textual context in adversarial environments, while ignoring the actual temporal dynamics in the video. To mitigate this issue, we design panoramic direct preference optimization (PanoDPO), which encourages LMMs to incorporate both visual and linguistic feature preferences simultaneously. Experimental results show that PanoDPO can effectively enhance the model’s robustness and reliability in temporal analysis.

Temporal Knowledge Graphs (TKGs) are vital for event prediction, yet current methods face limitations. Graph neural networks mainly depend on structural information, often overlooking semantic understanding and requiring high computational costs. Meanwhile, Large Language Models (LLMs) support zero-shot reasoning but lack sufficient capabilities to grasp the laws of historical event development. To tackle these challenges, we introduce a training-free Analogical Replay (AnRe) reasoning framework. Our approach retrieves similar events for queries through semantic-driven clustering and builds comprehensive historical contexts using a dual history extraction module that integrates long-term and short-term history. It then uses LLMs to generate analogical reasoning examples as contextual inputs, enabling the model to deeply understand historical patterns of similar events and improve its ability to predict unknown ones. Our experiments on four benchmarks show that AnRe significantly exceeds traditional training and existing LLM-based methods. Further ablation studies also confirm the effectiveness of the dual history extraction and analogical replay mechanisms.

Situational awareness refers to the capacity to perceive and comprehend the present context and anticipate forthcoming events, which plays a critical role in aiding decision-making, anticipating potential issues, and adapting to dynamic circumstances. Nevertheless, the situational awareness capabilities of large language models have not yet been comprehensively assessed. To address this, we propose SA-Bench, a comprehensive benchmark that covers three tiers of situational awareness capabilities, covering environment perception, situation comprehension and future projection. SA-Bench provides a comprehensive evaluation to explore the situational awareness capabilities of LLMs. We conduct extensive experiments on advanced LLMs, including GPT-4, LLaMA3, Qwen1.5, among others. Our experimental results indicate that even SOTA LLMs still exhibit substantial capability gaps compared to humans. In addition, we thoroughly analysis and examine the challenges encountered by LLMs across various tasks, as well as emphasize the deficiencies they confront. We hope SA-Bench will foster research within the field of situational awareness.

The same multi-word expressions may have different meanings in different sentences. They can be mainly divided into two categories, which are literal meaning and idiomatic meaning. Non-contextual-based methods perform poorly on this problem, and we need contextual embedding to understand the idiomatic meaning of multi-word expressions correctly. We use a pre-trained language model, which can provide a context-aware sentence embedding, to detect whether multi-word expression in the sentence is idiomatic usage.