论文检索

Deep Learning · Large Language Models

Wei Liu, Junlong Li, Xiwen Zhang, Fan Zhou, Yu Cheng, Junxian He

Self-evolving training—where models iteratively learn from their own outputs—has emerged as a key approach for complex reasoning tasks, addressing the scarcity of high-quality chain-of-thought data. However, its effectiveness in multimodal reasoning, a domain more intricate than text-only reasoning, remains underexplored, and the understanding of critical factors in this training paradigm remains limited. Furthermore, a central challenge for this training method is performance saturation, which impedes further improvements and scalability. Inspired by reinforcement learning (RL), in this paper, we reframe self-evolving training for multimodal reasoning through the lens of RL, identifying three pivotal factors: $\textit{Training Method}$, $\textit{Reward Model}$, and $\textit{Prompt Variation}$. Through systematic analysis, we establish relatively optimal design principles that significantly enhance multimodal reasoning capabilities. Moreover, delving deeper into training dynamics, we uncover the roots of saturation and propose a new automatic balancing mechanism to mitigate this limitation. Building on these insights, we propose M-STaR (**M**ultimodal **S**elf-evolving **T**r**a**ining for **R**easoning), a framework that achieves consistent performance gains across models of varying sizes and diverse benchmarks. All resources will be made publicly available.

Deep Learning · Large Language Models

Jiashu HE, Mingyu Ma, Jinxuan Fan, Dan Roth, Wei Wang, Alejandro Ribeiro

Existing approaches based on context prompting or reinforcement learning (RL) to improve the reasoning capacities of large language models (LLMs) depend on the LLMs' internal knowledge to produce reliable Chain-Of-Thought (CoT). However, no matter the size of LLMs, certain problems cannot be resolved in a single forward pass. Meanwhile, agent-based reasoning systems require access to a comprehensive nonparametric knowledge base, which is often costly or not feasible for use in scientific and niche domains. We present Graph Inspired Veracity Extrapolation (GIVE), a novel reasoning method that merges parametric and non-parametric memories to improve accurate reasoning with minimal external input. GIVE guides the LLM agent to select the most pertinent expert data ($\textbf{observe}$), engage in query-specific associative thinking ($\textbf{reflect}$), and then synthesize this information to produce the final output ($\textbf{speak}$). Extensive experiments demonstrated the following benefits of our framework: (1) GIVE increases the performance of LLMs across various sizes. (2) In some scenarios, GIVE allows smaller LLMs to surpass larger, more sophisticated ones in scientific tasks ($\textbf{GPT3.5T + GIVE > GPT4}$). (3) GIVE is effective on scientific and open-domain assessments. (4) GIVE is a training-free method that enables LLMs to tackle new problems that extend beyond their training data (up to $\textbf{43.5}$\% $\rightarrow$ $\textbf{88.2}$\% accuracy improvement). (5) GIVE allows LLM agents to reason using both restricted (very small) and noisy (very large) knowledge sources, accommodating knowledge graphs (KG) ranging from $\textbf{135}$ to more than $\textbf{840k}$ nodes. (6) The reasoning process involved in GIVE is fully interpretable. Our code is available at https://github.com/Jason-Tree/GIVE

Deep Learning · Large Language Models

Junbo Li, Zhangyang “Atlas” Wang, qiang liu

Offline preference alignment for language models such as Direct Preference Optimization (DPO) is favored for its effectiveness and simplicity, eliminating the need for costly reinforcement learning. Various offline algorithms have been developed for different data settings, yet they lack a unified understanding. In this study, we introduce Pior-Informed Preference Alignment (PIPA), a unified, RL-free probabilistic framework that formulates language model preference alignment as a Maximum Likelihood Estimation (MLE) problem with prior constraints. This method effectively accommodates both paired and unpaired data, as well as answer and step-level annotations. We illustrate that DPO and KTO are special cases with different prior constraints within our framework. By integrating different types of prior information, we developed two variations of PIPA: PIPA-M and PIPA-N. Both algorithms demonstrate a $3\sim10\%$ performance enhancement on the GSM8K and MATH benchmarks across all configurations, achieving these gains without additional training or computational costs compared to existing algorithms.

Reinforcement Learning · Deep RL

Jijia Liu, Feng Gao, Qingmin Liao, Chao Yu, Yu Wang

Reinforcement learning (RL) for continuous control often requires large amounts of online interaction data. Value-based RL methods can mitigate this burden by offering relatively high sample efficiency. Some studies further enhance sample efficiency by incorporating offline demonstration data to “kick-start” training, achieving promising results in continuous control. However, they typically compute the Q-function independently for each action dimension, neglecting interdependencies and making it harder to identify optimal actions when learning from suboptimal data, such as non-expert demonstration and online-collected data during the training process.To address these issues, we propose Auto-Regressive Soft Q-learning (ARSQ), a value-based RL algorithm that models Q-values in a coarse-to-fine, auto-regressive manner.First, ARSQ decomposes the continuous action space into discrete spaces in a coarse-to-fine hierarchy, enhancing sample efficiency for fine-grained continuous control tasks. Next, it auto-regressively predicts dimensional action advantages within each decision step, enabling more effective decision-making in continuous control tasks. We evaluate ARSQ on two continuous control benchmarks, RLBench and D4RL, integrating demonstration data into online training. On D4RL, which includes non-expert demonstrations, ARSQ achieves an average 1.62× performance improvement over SOTA value-based baseline. On RLBench, which incorporates expert demonstrations, ARSQ surpasses various baselines, demonstrating its effectiveness in learning from suboptimal online-collected data.

Reinforcement Learning · Deep RL

Yunhao Tang, Kunhao Zheng, Gabriel Synnaeve, REMI MUNOS

In this work, we investigate the merits of explicitly optimizing for inference time algorithmic performance during model training. We show how optimizing for inference time performance can improve overall model efficacy. We consider generic inference time objectives with $k$ samples, with focus on pass@$k$ and majority voting as two main applications. With language model training on reasoning datasets, we showcase the performance trade-off enabled by training with such objectives. When training on code generation tasks, we show that the approach significantly improves pass@$k$ objectives compared to the baseline method.

Deep Learning · Large Language Models

Ziliang Chen, Zhao-Rong Lai, Yufeng Yang, Liangda Fang, ZHANFU YANG, Liang Lin

Despite advancing language model (LM) alignment, direct preference optimization (DPO) falls short in LM reasoning with the free lunch from reinforcement learning (RL). As the breakthrough, this work proposes a new RL-free preference optimization method aiming to achieve DPO along with learning another LM, whose response generation policy holds the asymptotic equivalence with AlphaZero-like search, the apex of algorithms for complex reasoning missions like chess Go. While circumventing explicit value and reward modeling, the neural implicit tree search executed by the extra LM remains seeking to equip DPO with reasoning procedure technically akin to AlphaZero. Our experiments demonstrate that our methodology outperforms both regular DPO variants in human preference alignment, and MCTS-based LMs in mathematical reasoning and planning tasks.

Deep Learning · Large Language Models

Amrith Setlur, Nived Rajaraman, Sergey Levine, Aviral Kumar

Despite substantial advances in scaling test-time compute, an ongoing debate in the community is how it should be scaled up to enable continued and efficient improvements with scaling. There are largely two approaches: (i) distilling successful search or thinking traces; and (ii), using verification (e.g., 0/1 outcome rewards, or verifiers) to guide reinforcement learning (RL) and search algorithms. In this paper, we prove that finetuning LLMs with verifier-based (VB) methods based on RL or search is far superior to verifier-free (VF) approaches based on distilling or cloning search traces, given a fixed amount of compute/data budget. Further, we show that as we scale test-time compute (measured as the output token length) and training data, suboptimality of VF methods scales poorly compared to VB when the base pre-trained LLM presents a heterogeneous distribution over correct solution traces (e.g., different lengths, styles, etc.) and admits a non-sharp distribution over rewards on traces sampled from it. We formalize this condition using anti-concentration [Erdős 1945], implying a stronger result that VB methods scale better asymptotically, with the performance gap between VB and VF widening as test-time budget grows.We corroborate our theory empirically on didactic and math reasoning problems with 3/8/32B-sized pre-trained LLMs, where we find verification is crucial for scaling test-time compute.

Deep Learning · Large Language Models

Chengxing Jia, Ziniu Li, Pengyuan Wang, Yi-Chen Li, Zhenyu Hou, Yuxiao Dong, Yang Yu

Adapting Large Language Models (LLMs) to downstream tasks using Reinforcement Learning (RL) has proven to be an effective approach. However, LLMs do not inherently define the structure of an agent for RL training, particularly in terms of specifying the action space. This paper studies learning a compact latent action space to enhance the controllability and exploration of RL for LLMs. Inspired by reinforcement learning from observations, we propose **Co**ntrolling Large Language Models with **L**atent **A**ctions **CoLA**, a framework that integrates a latent action space into pre-trained LLMs. **CoLA** employs an \emph{inverse dynamics model} to extract latent actions conditioned on future tokens, ensuring that the next token prediction is partially influenced by these actions. Simultaneously, **CoLA** fine-tunes the pre-trained LLM to function as a \emph{language world model}, capable of incorporating latent actions as inputs. Additionally, **CoLA** trains a \emph{policy model} to generate actions within this language world model. The policy model can be trained via behavior cloning to mimic a standard language model or through RL to maximize task-specific rewards. In this work, we apply **CoLA** to the Llama-3.1-8B model. Our experiments demonstrate that, compared to RL with token-level actions, **CoLA**'s latent actions enable greater semantic diversity. For enhancing downstream tasks, we show that **CoLA** with RL achieves a score of 42.4 on the \emph{math500} benchmark, surpassing the baseline score of 38.2, and reaches 68.2 when augmented with a Monte Carlo Tree Search variant. Furthermore, **CoLA** with RL consistently improves performance on agent-based tasks without degrading the pre-trained LLM's capabilities, unlike the baseline. Finally, **CoLA** reduces computation time by half in tasks involving enhanced thinking prompts for LLMs via RL. These results highlight **CoLA**'s potential to advance RL-based adaptation of LLMs for downstream applications. The CoLA model is available at \url{https://huggingface.co/LAMDA-RL/Llama-3.1-CoLA-10B}.

Reinforcement Learning · Deep RL

Walter Mayor, Johan Obando-Ceron, Aaron Courville, Pablo Samuel Castro

The use of parallel actors for data collection has been an effective technique used in reinforcement learning (RL) algorithms. The manner in which data is collected in these algorithms, controlled via the number of parallel environments and the rollout length, induces a form of bias-variance trade-off; the number of training passes over the collected data, on the other hand, must strike a balance between sample efficiency and overfitting. We conduct an empirical analysis of these trade-offs on PPO, one of the most popular RL algorithms that uses parallel actors, and establish connections to network plasticity and, more generally, optimization stability. We examine its impact on network architectures, as well as the hyper-parameter sensitivity when scaling data. Our analyses indicate that larger dataset sizes can increase final performance across a variety of settings, and that scaling parallel environments is more effective than increasing rollout lengths. These findings highlight the critical role of data collection strategies in improving agent performance.

Deep Learning

Huaicheng Zhou, Zifeng Zhuang, Donglin Wang

The integration of Deep Neural Networks in Reinforcement Learning (RL) systems has led to remarkable progress in solving complex tasks but also introduced challenges like primacy bias and dead neurons. Primacy bias skews learning towards early experiences, while dead neurons diminish the network's capacity to acquire new knowledge. Traditional reset mechanisms aimed at addressing these issues often involve maintaining large replay buffers to train new networks or selectively resetting subsets of neurons. However, these approaches either incur prohibitive computational costs or reset network parameters without ensuring stability through recovery mechanisms, ultimately impairing learning efficiency. In this work, we introduce the novel concept of neuron regeneration, which combines reset mechanisms with knowledge recovery techniques. We also propose a new framework called Sustainable Backup Propagation(SBP) that effectively maintains plasticity in neural networks through this neuron regeneration process. The SBP framework achieves whole network neuron regeneration through two key procedures: cycle reset and inner distillation. Cycle reset involves a scheduled renewal of neurons, while inner distillation functions as a knowledge recovery mechanism at the neuron level. To validate our framework, we integrate SBP with Proximal Policy Optimization (PPO) and propose a novel distillation function for inner distillation. This integration results in Plastic PPO (P3O), a new algorithm that enables efficient cyclic regeneration of all neurons in the actor network. Extensive experiments demonstrate the approach effectively maintains policy plasticity and improves sample efficiency in reinforcement learning.

Reinforcement Learning · Deep RL

Long Ma, Fangwei Zhong, Yizhou Wang

The ability to adapt to new environments with noisy dynamics and unseen objectives is crucial for AI agents. In-context reinforcement learning (ICRL) has emerged as a paradigm to build adaptive policies, employing a **context** trajectory of the test-time interactions to infer the true task and the corresponding optimal policy efficiently without gradient updates. However, ICRL policies heavily rely on context trajectories, making them vulnerable to distribution shifts from training to testing and degrading performance, particularly in offline settings where the training data is static. In this paper, we highlight that most existing offline ICRL methods are trained for approximate Bayesian inference based on the training distribution, rendering them vulnerable to distribution shifts at test time and resulting in poor generalization. To address this, we introduce Behavior-agnostic Task Inference (BATI) for ICRL, a model-based maximum-likelihood solution to infer the task representation robustly. In contrast to previous methods that rely on a learned encoder as the approximate posterior, BATI focuses purely on dynamics, thus insulating itself against the behavior of the context collection policy. Experiments on MuJoCo environments demonstrate that BATI effectively interprets out-of-distribution contexts and outperforms other methods, even in the presence of significant environmental noise.

Reinforcement Learning · Deep RL

Guozheng Ma, Lu Li, Zilin Wang, Li Shen, Pierre-Luc Bacon, Dacheng Tao

Effectively scaling up deep reinforcement learning models has proven notoriously difficult due to network pathologies during training, motivating various targeted interventions such as periodic reset and architectural advances such as layer normalization. Instead of pursuing more complex modifications, we show that introducing static network sparsity alone can unlock further scaling potential beyond their dense counterparts with state-of-the-art architectures. This is achieved through simple one-shot random pruning, where a predetermined percentage of network weights are randomly removed once before training. Our analysis reveals that, in contrast to naively scaling up dense DRL networks, such sparse networks achieve both higher parameter efficiency for network expressivity and stronger resistance to optimization challenges like plasticity loss and gradient interference. We further extend our evaluation to visual and streaming RL scenarios, demonstrating the consistent benefits of network sparsity.

Reinforcement Learning · Deep RL

Dongchi Huang, Jiaqi WANG, Yang Li, Chunhe Xia, Tianle Zhang, Kaige Zhang

Partial observability presents a significant challenge for safe reinforcement learning, as it impedes the identification of potential risks and rewards. Leveraging specific types of privileged information during training to mitigate the effects of partial observability has yielded notable empirical successes. In this paper, we propose Asymmetric Constrained Partially Observable Markov Decision Processes (ACPOMDPs) to theoretically examine the advantages of incorporating privileged information. Building upon ACPOMDPs, we propose the Privileged Information Guided Dreamer, a model-based safe reinforcement learning approach that leverages privileged information to enhance the agent's safety and performance through privileged representation alignment and an asymmetric actor-critic structure. Our empirical results demonstrate that our approach significantly outperforms existing methods in terms of safety and task-centric performance. Meanwhile, compared to alternative privileged model-based reinforcement learning methods, our approach exhibits superior performance and ease of training.

Reinforcement Learning · Deep RL

Alexander Bukharin, Yixiao Li, Pengcheng He, Tuo Zhao

Reward design is a fundamental, yet challenging aspect of reinforcement learning (RL). Researchers typically utilize feedback signals from the environment to handcraft a reward function, but this process is not always effective due to the varying scale and intricate dependencies of the feedback signals. This paper shows by exploiting certain structures, one can ease the reward design process. Specifically, we propose a hierarchical reward design framework -- HERON for scenarios: (I) The feedback signals naturally present hierarchy; (II) The reward is sparse, but with less important surrogate feedback to help policy learning. Both scenarios allow us to design a hierarchical decision tree induced by the importance ranking of the feedback signals to compare RL trajectories. With such preference data, we can then train a reward model for policy learning. We apply HERON to several RL applications, and we find that our framework can not only train high performing agents on a variety of difficult tasks, but also provide additional benefits such as improved sample efficiency and robustness.

Reinforcement Learning

Suning Huang, Zheyu Zhang, Tianhai Liang, Yihan Xu, Zhehao Kou, Chenhao Lu, Guowei Xu, Zhengrong Xue, Huazhe Xu

Visual deep reinforcement learning (RL) enables robots to acquire skills from visual input for unstructured tasks. However, current algorithms suffer from low sample efficiency, limiting their practical applicability. In this work, we present MENTOR, a method that improves both the *architecture* and *optimization* of RL agents. Specifically, MENTOR replaces the standard multi-layer perceptron (MLP) with a mixture-of-experts (MoE) backbone and introduces a task-oriented perturbation mechanism. MENTOR outperforms state-of-the-art methods across three simulation benchmarks and achieves an average of 83\% success rate on three challenging real-world robotic manipulation tasks, significantly surpassing the 32% success rate of the strongest existing model-free visual RL algorithm. These results underscore the importance of sample efficiency in advancing visual RL for real-world robotics. Experimental videos are available at https://suninghuang19.github.io/mentor_page/.

Deep Learning · Large Language Models

Zhenyu Hou, Xin Lv, Rui Lu, Jiajie Zhang, Yujiang Li, Zijun Yao, Juanzi Li, Jie Tang, Yuxiao Dong

Large language models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks. However, existing approaches mainly rely on imitation learning and struggle to achieve effective test-time scaling. While reinforcement learning (RL) holds promise for enabling self-exploration, recent attempts yield modest improvements in complex reasoning. In this paper, we present T1 to scale RL by encouraging exploration and understand inference scaling. We first initialize the LLM using synthesized chain-of-thought data that integrates trial-and-error and self-verification. To scale RL training, we promote increased sampling diversity through over-sampling. We demonstrate that T1 with open LLMs as its base exhibits inference scaling behavior and achieves superior performance on challenging math reasoning benchmarks. More importantly, we present a simple strategy to examine inference scaling, where increased inference budgets directly lead to T1’s better performance without any additional verification. The model weights and training data are publicly available at https://github.com/THUDM/T1.

Reinforcement Learning · Deep RL

Marco Cusumano-Towner, David Hafner, Alexander Hertzberg, Brody Huval, Aleksei Petrenko, Eugene Vinitsky, Erik Wijmans, Taylor Killian, Stuart Bowers, Ozan Sener 等

Self-play has powered breakthroughs in two-player and multi-player games. Here we show that self-play is a surprisingly effective strategy in another domain. We show that robust and naturalistic driving emerges entirely from self-play in simulation at unprecedented scale -- 1.6 billion km of driving. This is enabled by Gigaflow, a batched simulator that can synthesize and train on 42 years of subjective driving experience per hour on a single 8-GPU node. The resulting policy achieves state-of-the-art performance on three independent autonomous driving benchmarks. The policy outperforms the prior state of the art when tested on recorded real-world scenarios, amidst human drivers, without ever seeing human data during training. The policy is realistic when assessed against human references and achieves unprecedented robustness, averaging 17.5 years of continuous driving between incidents in simulation.

Reinforcement Learning · Deep RL

Yucen Wang, Rui Yu, Shenghua Wan, Le Gan, De-Chuan Zhan

Foundation Models (FMs) and World Models (WMs) offer complementary strengths in task generalization at different levels. In this work, we propose FOUNDER, a framework that integrates the generalizable knowledge embedded in FMs with the dynamic modeling capabilities of WMs to enable open-ended task solving in embodied environments in a reward-free manner. We learn a mapping function that grounds FM representations in the WM state space, effectively inferring the agent's physical states in the world simulator from external observations. This mapping enables the learning of a goal-conditioned policy through imagination during behavior learning, with the mapped task serving as the goal state. Our method leverages the predicted temporal distance to the goal state as an informative reward signal. FOUNDER demonstrates superior performance on various multi-task offline visual control benchmarks, excelling in capturing the deep-level semantics of tasks specified by text or videos, particularly in scenarios involving complex observations or domain gaps where prior methods struggle. The consistency of our learned reward function with the ground-truth reward is also empirically validated. Our project website is https://sites.google.com/view/founder-rl.

Reinforcement Learning · Deep RL

Harry Mead, Clarissa Costen, Bruno Lacerda, Nick Hawes

When optimising for conditional value at risk (CVaR) using policy gradients (PG), current methods rely on discarding a large proportion of trajectories, resulting in poor sample efficiency. We propose a reformulation of the CVaR optimisation problem by capping the total return of trajectories used in training, rather than simply discarding them, and show that this is equivalent to the original problem if the cap is set appropriately. We show, with empirical results in an number of environments, that this reformulation of the problem results in consistently improved performance compared to baselines. We have made all our code available here: \url{https://github.com/HarryMJMead/cvar-return-capping}.

Reinforcement Learning · Deep RL

Xiaoyi Dong, Jian Cheng, Xi Zhang

The Soft Actor-Critic (SAC) algorithm with a Gaussian policy has become a mainstream implementation for realizing the Maximum Entropy Reinforcement Learning (MaxEnt RL) objective, which incorporates entropy maximization to encourage exploration and enhance policy robustness. While the Gaussian policy performs well on simpler tasks, its exploration capacity and potential performance in complex multi-goal RL environments are limited by its inherent unimodality. In this paper, we employ the diffusion model, a powerful generative model capable of capturing complex multimodal distributions, as the policy representation to fulfill the MaxEnt RL objective, developing a method named MaxEnt RL with Diffusion Policy (MaxEntDP). Our method enables efficient exploration and brings the policy closer to the optimal MaxEnt policy. Experimental results on Mujoco benchmarks show that MaxEntDP outperforms the Gaussian policy and other generative models within the MaxEnt RL framework, and performs comparably to other state-of-the-art diffusion-based online RL algorithms. Our code is available at https://github.com/diffusionyes/MaxEntDP.