Xiaoyin Chen

Xiaoyin Chen, Canwen Xu, Yite Wang et al.

We introduce Learning to Self-Evolve (LSE), a reinforcement learning framework that trains large language models (LLMs) to improve their own contexts at test time. We situate LSE in the setting of test-time self-evolution, where a model iteratively refines its context from feedback on seen problems to perform better on new ones. Existing approaches rely entirely on the inherent reasoning ability of the model and never explicitly train it for this task. LSE reduces the multi-step evolution problem to a single-step RL objective, where each context edit is rewarded by the improvement in downstream performance. We pair this objective with a tree-guided evolution loop. On Text-to-SQL generation (BIRD) and general question answering (MMLU-Redux), a 4B-parameter model trained with LSE outperforms self-evolving policies powered by GPT-5 and Claude Sonnet 4.5, as well as prompt optimization methods including GEPA and TextGrad, and transfers to guide other models without additional training. Our results highlight the effectiveness of treating self-evolution as a learnable skill.

Yuyang Zhang, Yifu Zhang, Xuehai Zhou et al.

While empirical scaling laws for LLM reasoning are well-documented, the theoretical mechanisms governing out-of-distribution (OOD) generalization remain elusive. We formalize reasoning via optimal transport, projecting discrete trajectories into a continuous metric space to quantify domain shifts using the Wasserstein-1 distance. Invoking Kantorovich duality, we bound OOD generalization via architectural Lipschitz continuity and functional approximation limits. This exposes two primary constraints. First, position-dependent attention (e.g., Absolute Positional Encoding) fails to preserve shift invariance, yielding an $Ω(1)$ Lipschitz constant and expected risk, whereas shift-invariant mechanisms (e.g., Rotary Embeddings) preserve equivariance and bound the error. Second, by mapping sequential backtracking to a Dyck-$k$ language, we establish a strict circuit depth lower bound for $\text{TC}^0$ Transformers. Scaling physical layer depth is necessary to avert representation collapse -- a constraint that scaling representation width cannot bypass due to irreducible approximation bounds in Barron spaces. Evaluations across 54 Transformer configurations on combinatorial search corroborate these bounds, demonstrating that generalization risk degrades monotonically with the Wasserstein domain shift.

Junyi Tao, Xiaoyin Chen, Nelson F. Liu

Large language models (LMs) are capable of in-context learning from a few demonstrations (example-label pairs) to solve new tasks during inference. Despite the intuitive importance of high-quality demonstrations, previous work has observed that, in some settings, ICL performance is minimally affected by irrelevant labels (Min et al., 2022). We hypothesize that LMs perform ICL with irrelevant labels via two sequential processes: an inference function that solves the task, followed by a verbalization function that maps the inferred answer to the label space. Importantly, we hypothesize that the inference function is invariant to remappings of the label space (e.g., "true"/"false" to "cat"/"dog"), enabling LMs to share the same inference function across settings with different label words. We empirically validate this hypothesis with controlled layer-wise interchange intervention experiments. Our findings confirm the hypotheses on multiple datasets and tasks (natural language inference, sentiment analysis, and topic classification) and further suggest that the two functions can be localized in specific layers across various open-sourced models, including GEMMA-7B, MISTRAL-7B-V0.3, GEMMA-2-27B, and LLAMA-3.1-70B.

Alexandre Piché, Ehsan Kamalloo, Rafael Pardinas et al.

Reinforcement Learning (RL) is increasingly utilized to enhance the reasoning capabilities of Large Language Models (LLMs). However, effectively scaling these RL methods presents significant challenges, primarily due to the difficulty in maintaining high AI accelerator utilization without generating stale, off-policy data that harms common RL algorithms. This paper introduces PipelineRL, an approach designed to achieve a superior trade-off between hardware efficiency and data on-policyness for LLM training. PipelineRL employs concurrent asynchronous data generation and model training, distinguished by the novel in-flight weight updates. This mechanism allows the LLM generation engine to receive updated model weights with minimal interruption during the generation of token sequences, thereby maximizing both the accelerator utilization and the freshness of training data. Experiments conducted on long-form reasoning tasks using 128 H100 GPUs demonstrate that PipelineRL achieves approximately $\sim 2x$ faster learning compared to conventional RL baselines while maintaining highly on-policy training data. A scalable and modular open-source implementation of PipelineRL is also released as a key contribution.

Thomas Jiralerspong, Xiaoyin Chen, Yash More et al.

We propose a novel framework that leverages LLMs for full causal graph discovery. While previous LLM-based methods have used a pairwise query approach, this requires a quadratic number of queries which quickly becomes impractical for larger causal graphs. In contrast, the proposed framework uses a breadth-first search (BFS) approach which allows it to use only a linear number of queries. We also show that the proposed method can easily incorporate observational data when available, to improve performance. In addition to being more time and data-efficient, the proposed framework achieves state-of-the-art results on real-world causal graphs of varying sizes. The results demonstrate the effectiveness and efficiency of the proposed method in discovering causal relationships, showcasing its potential for broad applicability in causal graph discovery tasks across different domains.

Xiaoyin Chen, Jiarui Lu, Minsu Kim et al. · mila

Reinforcement learning (RL) has proven effective for fine-tuning large language models (LLMs), significantly enhancing their reasoning abilities in domains such as mathematics and code generation. A crucial factor influencing RL fine-tuning success is the training curriculum: the order in which training problems are presented. While random curricula serve as common baselines, they remain suboptimal; manually designed curricula often rely heavily on heuristics, and online filtering methods can be computationally prohibitive. To address these limitations, we propose Self-Evolving Curriculum (SEC), an automatic curriculum learning method that learns a curriculum policy concurrently with the RL fine-tuning process. Our approach formulates curriculum selection as a non-stationary Multi-Armed Bandit problem, treating each problem category (e.g., difficulty level or problem type) as an individual arm. We leverage the absolute advantage from policy gradient methods as a proxy measure for immediate learning gain. At each training step, the curriculum policy selects categories to maximize this reward signal and is updated using the TD(0) method. Across three distinct reasoning domains: planning, inductive reasoning, and mathematics, our experiments demonstrate that SEC significantly improves models' reasoning capabilities, enabling better generalization to harder, out-of-distribution test problems. Additionally, our approach achieves better skill balance when fine-tuning simultaneously on multiple reasoning domains. These findings highlight SEC as a promising strategy for RL fine-tuning of LLMs.

Jiarui Lu, Xiaoyin Chen, Stephen Zhewen Lu et al.

Proteins adopt multiple structural conformations to perform their diverse biological functions, and understanding these conformations is crucial for advancing drug discovery. Traditional physics-based simulation methods often struggle with sampling equilibrium conformations and are computationally expensive. Recently, deep generative models have shown promise in generating protein conformations as a more efficient alternative. However, these methods predominantly rely on the diffusion process within a 3D geometric space, which typically centers around the vicinity of metastable states and is often inefficient in terms of runtime. In this paper, we introduce Structure Language Modeling (SLM) as a novel framework for efficient protein conformation generation. Specifically, the protein structures are first encoded into a compact latent space using a discrete variational auto-encoder, followed by conditional language modeling that effectively captures sequence-specific conformation distributions. This enables a more efficient and interpretable exploration of diverse ensemble modes compared to existing methods. Based on this general framework, we instantiate SLM with various popular LM architectures as well as proposing the ESMDiff, a novel BERT-like structure language model fine-tuned from ESM3 with masked diffusion. We verify our approach in various scenarios, including the equilibrium dynamics of BPTI, conformational change pairs, and intrinsically disordered proteins. SLM provides a highly efficient solution, offering a 20-100x speedup than existing methods in generating diverse conformations, shedding light on promising avenues for future research.

Hongyi James Cai, Junlin Wang, Xiaoyin Chen et al.

Recent breakthroughs in large language models (LLMs) have effectively improved their reasoning abilities, particularly on mathematical and logical problems that have verifiable answers, through techniques such as supervised finetuning (SFT) and reinforcement learning (RL). Prior research indicates that RL effectively internalizes search strategies, enabling long chain-of-thought (CoT) reasoning, with backtracking emerging naturally as a learned capability. However, the precise benefits of backtracking, specifically, how significantly it contributes to reasoning improvements and the optimal extent of its use, remain poorly understood. In this work, we systematically investigate the dynamics between SFT and RL on eight reasoning tasks: Countdown, Sudoku, Arc 1D, Geometry, Color Cube Rotation, List Functions, Zebra Puzzles, and Self Reference. Our findings highlight that short CoT sequences used in SFT as a warm-up do have moderate contribution to RL training, compared with cold-start RL; however such contribution diminishes when tasks become increasingly difficult. Motivated by this observation, we construct synthetic datasets varying systematically in the number of backtracking steps and conduct controlled experiments to isolate the influence of either the correctness (content) or the structure (i.e., backtrack frequency). We find that (1) longer CoT with backtracks generally induce better and more stable RL training, (2) more challenging problems with larger search space tend to need higher numbers of backtracks during the SFT stage. Additionally, we demonstrate through experiments on distilled data that RL training is largely unaffected by the correctness of long CoT sequences, suggesting that RL prioritizes structural patterns over content correctness. Collectively, our results offer practical insights into designing optimal training strategies to effectively scale reasoning in LLMs.

Matthew Ho, Vincent Zhu, Xiaoyin Chen et al. · mila

Reasoning is a fundamental substrate for solving novel and complex problems. Deliberate efforts in learning and developing frameworks around System 2 reasoning have made great strides, yet problems of sufficient complexity remain largely out of reach for open models. To address this gap, we examine the potential of Generative Flow Networks as a fine-tuning method for LLMs to unlock advanced reasoning capabilities. In this paper, we present a proof of concept in the domain of formal reasoning, specifically in the Neural Theorem Proving (NTP) setting, where proofs specified in a formal language such as Lean can be deterministically and objectively verified. Unlike classical reward-maximization reinforcement learning, which frequently over-exploits high-reward actions and fails to effectively explore the state space, GFlowNets have emerged as a promising approach for sampling compositional objects, improving generalization, and enabling models to maintain diverse hypotheses. Our early results demonstrate GFlowNet fine-tuning's potential for enhancing model performance in a search setting, which is especially relevant given the paradigm shift towards inference time compute scaling and "thinking slowly."

Jiarui Lu, Xiaoyin Chen, Stephen Zhewen Lu et al.

Protein dynamics play a crucial role in protein biological functions and properties, and their traditional study typically relies on time-consuming molecular dynamics (MD) simulations conducted in silico. Recent advances in generative modeling, particularly denoising diffusion models, have enabled efficient accurate protein structure prediction and conformation sampling by learning distributions over crystallographic structures. However, effectively integrating physical supervision into these data-driven approaches remains challenging, as standard energy-based objectives often lead to intractable optimization. In this paper, we introduce Energy-based Alignment (EBA), a method that aligns generative models with feedback from physical models, efficiently calibrating them to appropriately balance conformational states based on their energy differences. Experimental results on the MD ensemble benchmark demonstrate that EBA achieves state-of-the-art performance in generating high-quality protein ensembles. By improving the physical plausibility of generated structures, our approach enhances model predictions and holds promise for applications in structural biology and drug discovery.

Sanxing Chen, Xiaoyin Chen, Yukun Huang et al.

While Large Language Models (LLMs) hold promise to become autonomous agents, they often explore suboptimally in sequential decision-making. Recent work has sought to enhance this capability via supervised fine-tuning (SFT) or reinforcement learning (RL), improving regret on the classic multi-armed bandit task. However, it remains unclear how these learning methods shape exploration strategies and how well they generalize. We investigate both paradigms by training LLMs with SFT on expert trajectories and RL with a range of tailored reward signals including a strategic, regret-shaped reward to reduce variance, and an algorithmic reward that enables oracle imitation. The resulting agents outperform pre-trained models and achieve performance comparable to Upper Confidence Bound (UCB) and Thompson Sampling, with robust generalization to 6x longer horizons and across bandit families. Behavioral analysis reveals that gains often stem from more sophisticated but greedier exploitation: RL/SFT agents are more prone to early catastrophic failure than pre-trained models, prematurely abandoning exploration. Furthermore, agents trained to imitate UCB learn to outperform their teacher by adopting more exploitative variants. Our findings clarify when each training paradigm is preferable and advocate tailored reward design and evaluation beyond average regret to promote robust exploratory behavior.

Minsu Kim, Jean-Pierre Falet, Oliver E. Richardson et al. · mila

Chain-of-Thought (CoT) reasoning has advanced the capabilities and transparency of language models (LMs); however, reasoning chains can contain inaccurate statements that reduce performance and trustworthiness. To address this, we propose to augment each reasoning step in a CoT with a latent veracity (or correctness) variable. To efficiently explore this expanded space, we introduce Veracity Search (VS), a discrete search algorithm over veracity assignments. It performs otherwise intractable inference in the posterior distribution over latent veracity values by leveraging the LM's joint likelihood over veracity and the final answer as a proxy reward. This efficient inference-time verification method facilitates supervised fine-tuning of an Amortized Veracity Inference (AVI) machine by providing pseudo-labels for veracity. AVI generalizes VS, enabling accurate zero-shot veracity inference in novel contexts. Empirical results demonstrate that VS reliably identifies errors in logical (ProntoQA), mathematical (GSM8K), and commonsense (CommonsenseQA) reasoning benchmarks, with AVI achieving comparable zero-shot accuracy. Finally, we demonstrate the utility of latent veracity inference for providing feedback during self-correction and self-improvement.

Xiaoyin Chen, Sam Wiseman

Given BM25's enduring competitiveness as an information retrieval baseline, we investigate to what extent it can be even further improved by augmenting and re-weighting its sparse query-vector representation. We propose an approach to learning an augmentation and a re-weighting end-to-end, and we find that our approach improves performance over BM25 while retaining its speed. We furthermore find that the learned augmentations and re-weightings transfer well to unseen datasets.

Gabriel Hope, Madina Abdrakhmanova, Xiaoyin Chen et al.

We develop a new framework for learning variational autoencoders and other deep generative models that balances generative and discriminative goals. Our framework optimizes model parameters to maximize a variational lower bound on the likelihood of observed data, subject to a task-specific prediction constraint that prevents model misspecification from leading to inaccurate predictions. We further enforce a consistency constraint, derived naturally from the generative model, that requires predictions on reconstructed data to match those on the original data. We show that these two contributions -- prediction constraints and consistency constraints -- lead to promising image classification performance, especially in the semi-supervised scenario where category labels are sparse but unlabeled data is plentiful. Our approach enables advances in generative modeling to directly boost semi-supervised classification performance, an ability we demonstrate by augmenting deep generative models with latent variables capturing spatial transformations.