Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models

Language has long been conceived as an essential tool for human reasoning. The breakthrough of Large Language Models (LLMs) has sparked significant research interest in leveraging these models to tackle complex reasoning tasks. Researchers have moved beyond simple autoregressive token generation by introducing the concept of "thought" -- a sequence of tokens representing intermediate steps in the reasoning process. This innovative paradigm enables LLMs' to mimic complex human reasoning processes, such as tree search and reflective thinking. Recently, an emerging trend of learning to reason has applied reinforcement learning (RL) to train LLMs to master reasoning processes. This approach enables the automatic generation of high-quality reasoning trajectories through trial-and-error search algorithms, significantly expanding LLMs' reasoning capacity by providing substantially more training data. Furthermore, recent studies demonstrate that encouraging LLMs to "think" with more tokens during test-time inference can further significantly boost reasoning accuracy. Therefore, the train-time and test-time scaling combined to show a new research frontier -- a path toward Large Reasoning Model. The introduction of OpenAI's o1 series marks a significant milestone in this research direction. In this survey, we present a comprehensive review of recent progress in LLM reasoning. We begin by introducing the foundational background of LLMs and then explore the key technical components driving the development of large reasoning models, with a focus on automated data construction, learning-to-reason techniques, and test-time scaling. We also analyze popular open-source projects at building large reasoning models, and conclude with open challenges and future research directions.

A Survey on Responsible LLMs: Inherent Risk, Malicious Use, and Mitigation Strategy

While large language models (LLMs) present significant potential for supporting numerous real-world applications and delivering positive social impacts, they still face significant challenges in terms of the inherent risk of privacy leakage, hallucinated outputs, and value misalignment, and can be maliciously used for generating toxic content and unethical purposes after been jailbroken. Therefore, in this survey, we present a comprehensive review of recent advancements aimed at mitigating these issues, organized across the four phases of LLM development and usage: data collecting and pre-training, fine-tuning and alignment, prompting and reasoning, and post-processing and auditing. We elaborate on the recent advances for enhancing the performance of LLMs in terms of privacy protection, hallucination reduction, value alignment, toxicity elimination, and jailbreak defenses. In contrast to previous surveys that focus on a single dimension of responsible LLMs, this survey presents a unified framework that encompasses these diverse dimensions, providing a comprehensive view of enhancing LLMs to better serve real-world applications.

SmartAgent: Chain-of-User-Thought for Embodied Personalized Agent in Cyber World

Recent advances in embodied agents with multimodal perception and reasoning capabilities based on large vision-language models (LVLMs), excel in autonomously interacting either real or cyber worlds, helping people make intelligent decisions in complex environments. However, the current works are normally optimized by golden action trajectories or ideal task-oriented solutions toward a definitive goal. This paradigm considers limited user-oriented factors, which could be the reason for their performance reduction in a wide range of personal assistant applications. To address this, we propose Chain-of-User-Thought (COUT), a novel embodied reasoning paradigm that takes a chain of thought from basic action thinking to explicit and implicit personalized preference thought to incorporate personalized factors into autonomous agent learning. To target COUT, we introduce SmartAgent, an agent framework perceiving cyber environments and reasoning personalized requirements as 1) interacting with GUI to access an item pool, 2) generating users' explicit requirements implied by previous actions, and 3) recommending items to fulfill users' implicit requirements. To demonstrate SmartAgent's capabilities, we also create a brand-new dataset SmartSpot that offers a full-stage personalized action-involved environment. To our best knowledge, our work is the first to formulate the COUT process, serving as a preliminary attempt towards embodied personalized agent learning. Our extensive experiments on SmartSpot illuminate SmartAgent's functionality among a series of embodied and personalized sub-tasks. We will release code and data upon paper notification at \url{https://github.com/tsinghua-fib-lab/SmartAgent}.

Textured Gaussians for Enhanced 3D Scene Appearance Modeling

3D Gaussian Splatting (3DGS) has recently emerged as a state-of-the-art 3D reconstruction and rendering technique due to its high-quality results and fast training and rendering time. However, pixels covered by the same Gaussian are always shaded in the same color up to a Gaussian falloff scaling factor. Furthermore, the finest geometric detail any individual Gaussian can represent is a simple ellipsoid. These properties of 3DGS greatly limit the expressivity of individual Gaussian primitives. To address these issues, we draw inspiration from texture and alpha mapping in traditional graphics and integrate it with 3DGS. Specifically, we propose a new generalized Gaussian appearance representation that augments each Gaussian with alpha~(A), RGB, or RGBA texture maps to model spatially varying color and opacity across the extent of each Gaussian. As such, each Gaussian can represent a richer set of texture patterns and geometric structures, instead of just a single color and ellipsoid as in naive Gaussian Splatting. Surprisingly, we found that the expressivity of Gaussians can be greatly improved by using alpha-only texture maps, and further augmenting Gaussians with RGB texture maps achieves the highest expressivity. We validate our method on a wide variety of standard benchmark datasets and our own custom captures at both the object and scene levels. We demonstrate image quality improvements over existing methods while using a similar or lower number of Gaussians.

TopV-Nav: Unlocking the Top-View Spatial Reasoning Potential of MLLM for Zero-shot Object Navigation

The Zero-Shot Object Navigation (ZSON) task requires embodied agents to find a previously unseen object by navigating in unfamiliar environments. Such a goal-oriented exploration heavily relies on the ability to perceive, understand, and reason based on the spatial information of the environment. However, current LLM-based approaches convert visual observations to language descriptions and reason in the linguistic space, leading to the loss of spatial information. In this paper, we introduce TopV-Nav, a MLLM-based method that directly reasons on the top-view map with complete spatial information. To fully unlock the MLLM's spatial reasoning potential in top-view perspective, we propose the Adaptive Visual Prompt Generation (AVPG) method to adaptively construct semantically-rich top-view map. It enables the agent to directly utilize spatial information contained in the top-view map to conduct thorough reasoning. Besides, we design a Dynamic Map Scaling (DMS) mechanism to dynamically zoom top-view map at preferred scales, enhancing local fine-grained reasoning. Additionally, we devise a Target-Guided Navigation (TGN) mechanism to predict and to utilize target locations, facilitating global and human-like exploration. Experiments on MP3D and HM3D benchmarks demonstrate the superiority of our TopV-Nav, e.g., $+3.9\%$ SR and $+2.0\%$ SPL absolute improvements on HM3D.

All-domain Moveline Evolution Network for Click-Through Rate Prediction

E-commerce app users exhibit behaviors that are inherently logically consistent. A series of multi-scenario user behaviors interconnect to form the scene-level all-domain user moveline, which ultimately reveals the user's true intention. Traditional CTR prediction methods typically focus on the item-level interaction between the target item and the historically interacted items. However, the scene-level interaction between the target item and the user moveline remains underexplored. There are two challenges when modeling the interaction with preceding all-domain user moveline: (i) Heterogeneity between items and scenes: Unlike traditional user behavior sequences that utilize items as carriers, the user moveline utilizes scenes as carriers. The heterogeneity between items and scenes complicates the process of aligning interactions within a unified representation space. (ii) Temporal misalignment of linked scene-level and item-level behaviors: In the preceding user moveline with a fixed sampling length, certain critical scene-level behaviors are closely linked to subsequent item-level behaviors. However, it is impossible to establish a complete temporal alignment that clearly identifies which specific scene-level behaviors correspond to which item-level behaviors. To address these challenges and pioneer modeling user intent from the perspective of the all-domain moveline, we propose All-domain Moveline Evolution Network (AMEN). AMEN not only transfers interactions between items and scenes to homogeneous representation spaces, but also introduces a Temporal Sequential Pairwise (TSP) mechanism to understand the nuanced associations between scene-level and item-level behaviors, ensuring that the all-domain user moveline differentially influences CTR predictions for user's favored and unfavored items. Online A/B testing demonstrates that our method achieves a +11.6% increase in CTCVR.

Collaborative Contrastive Network for Click-Through Rate Prediction

E-commerce platforms provide entrances for customers to enter mini-apps to meet their specific shopping needs. At the entrance of a mini-app, a trigger item recommended based on customers' historical preferences, is displayed to attract customers to enter the mini-app. Existing Click-Through Rate (CTR) prediction approaches have two significant weaknesses: (i) A portion of customer entries is driven by their interest in the mini-app itself rather than the trigger item. In such cases, approaches highly hinging on the trigger item tend to recommend similar items, thus misunderstanding the customers' real intention; (ii) Approaches that consider customers' intention toward mini-apps, require the regular existence of mini-apps for customers to cultivate routine shopping habits, making such approaches less robust for mini-apps that are available for only short periods (1 or 3 days) in Explosive Promotional Scenarios (EPS), such as the Black Friday and China's Double 11 Shopping Carnival. To address the above-mentioned issues, we introduce a more general and robust CTR prediction approach, dubbed Collaborative Contrastive Network (CCN). Given a user, CCN learns to identify two item clusters that can represent the user's interests and disinterests, via leveraging the collaborative relationship of co-click/co-non-click or the non-collaborative relationship of mono-click as the supervision signal for contrastive learning. This paradigm does not need to explicitly estimate user's binary entry intention and avoids amplifying the impact of the trigger item. Online A/B testing on large-scale real-world data demonstrates that CCN sets a new state-of-the-art performance on Taobao, boosting CTR by 12.3% and order volume by 12.7%.

LLM-assisted Explicit and Implicit Multi-interest Learning Framework for Sequential Recommendation

Multi-interest modeling in current recommender systems (RS) is mainly based on user behavioral data, capturing user interest preferences from multiple dimensions. However, since behavioral data is implicit and often highly sparse, it is challenging to understand users' complex and diverse interests. Recent studies have shown that the rich semantic information in the text can effectively supplement the deficiencies of behavioral data. Despite this, it is still difficult for small models to directly extract semantic features associated with users' deep interests. That is, how to effectively align semantics with behavioral information to form a more comprehensive and accurate understanding of user interests has become a critical research problem.To address this, we propose an LLM-assisted explicit and implicit multi-interest learning framework (named EIMF) to model user interests on two levels: behavior and semantics. The framework consists of two parts: Implicit Behavioral Interest Module (IBIM) and Explicit Semantic Interest Module (ESIM). The traditional multi-interest RS model in IBIM can learn users' implicit behavioral interests from interactions with items. In ESIM, we first adopt a clustering algorithm to select typical samples and design a prompting strategy on LLM to obtain explicit semantic interests. Furthermore, in the training phase, the semantic interests of typical samples can enhance the representation learning of behavioral interests based on the multi-task learning on semantic prediction and modality alignment. Therefore, in the inference stage, accurate recommendations can be achieved with only the user's behavioral data. Extensive experiments on real-world datasets demonstrate the effectiveness of the proposed EIMF framework, which effectively and efficiently combines small models with LLM to improve the accuracy of multi-interest modeling.

Planar Reflection-Aware Neural Radiance Fields

Neural Radiance Fields (NeRF) have demonstrated exceptional capabilities in reconstructing complex scenes with high fidelity. However, NeRF's view dependency can only handle low-frequency reflections. It falls short when handling complex planar reflections, often interpreting them as erroneous scene geometries and leading to duplicated and inaccurate scene representations. To address this challenge, we introduce a reflection-aware NeRF that jointly models planar reflectors, such as windows, and explicitly casts reflected rays to capture the source of the high-frequency reflections. We query a single radiance field to render the primary color and the source of the reflection. We propose a sparse edge regularization to help utilize the true sources of reflections for rendering planar reflections rather than creating a duplicate along the primary ray at the same depth. As a result, we obtain accurate scene geometry. Rendering along the primary ray results in a clean, reflection-free view, while explicitly rendering along the reflected ray allows us to reconstruct highly detailed reflections. Our extensive quantitative and qualitative evaluations of real-world datasets demonstrate our method's enhanced performance in accurately handling reflections.

Enhancing ID-based Recommendation with Large Language Models

Large Language Models (LLMs) have recently garnered significant attention in various domains, including recommendation systems. Recent research leverages the capabilities of LLMs to improve the performance and user modeling aspects of recommender systems. These studies primarily focus on utilizing LLMs to interpret textual data in recommendation tasks. However, it's worth noting that in ID-based recommendations, textual data is absent, and only ID data is available. The untapped potential of LLMs for ID data within the ID-based recommendation paradigm remains relatively unexplored. To this end, we introduce a pioneering approach called "LLM for ID-based Recommendation" (LLM4IDRec). This innovative approach integrates the capabilities of LLMs while exclusively relying on ID data, thus diverging from the previous reliance on textual data. The basic idea of LLM4IDRec is that by employing LLM to augment ID data, if augmented ID data can improve recommendation performance, it demonstrates the ability of LLM to interpret ID data effectively, exploring an innovative way for the integration of LLM in ID-based recommendation. We evaluate the effectiveness of our LLM4IDRec approach using three widely-used datasets. Our results demonstrate a notable improvement in recommendation performance, with our approach consistently outperforming existing methods in ID-based recommendation by solely augmenting input data.