LEGOMem: Modular Procedural Memory for Multi-agent LLM Systems for Workflow Automation

We introduce LEGOMem, a modular procedural memory framework for multi-agent large language model (LLM) systems in workflow automation. LEGOMem decomposes past task trajectories into reusable memory units and flexibly allocates them across orchestrators and task agents to support planning and execution. To explore the design space of memory in multi-agent systems, we use LEGOMem as a lens and conduct a systematic study of procedural memory in multi-agent systems, examining where memory should be placed, how it should be retrieved, and which agents benefit most. Experiments on the OfficeBench benchmark show that orchestrator memory is critical for effective task decomposition and delegation, while fine-grained agent memory improves execution accuracy. We find that even teams composed of smaller language models can benefit substantially from procedural memory, narrowing the performance gap with stronger agents by leveraging prior execution traces for more accurate planning and tool use. These results position LEGOMem as both a practical framework for memory-augmented agent systems and a research tool for understanding memory design in multi-agent workflow automation.

Enhancing Reasoning Capabilities of Small Language Models with Blueprints and Prompt Template Search

Small language models (SLMs) offer promising and efficient alternatives to large language models (LLMs). However, SLMs' limited capacity restricts their reasoning capabilities and makes them sensitive to prompt variations. To address these challenges, we propose a novel framework that enhances SLM reasoning capabilities through LLM generated blueprints. The blueprints provide structured, high-level reasoning guides that help SLMs systematically tackle related problems. Furthermore, our framework integrates a prompt template search mechanism to mitigate the SLMs' sensitivity to prompt variations. Our framework demonstrates improved SLM performance across various tasks, including math (GSM8K), coding (MBPP), and logic reasoning (BBH). Our approach improves the reasoning capabilities of SLMs without increasing model size or requiring additional training, offering a lightweight and deployment-friendly solution for on-device or resource-constrained environments.

Anyprefer: An Agentic Framework for Preference Data Synthesis

High-quality preference data is essential for aligning foundation models with human values through preference learning. However, manual annotation of such data is often time-consuming and costly. Recent methods often adopt a self-rewarding approach, where the target model generates and annotates its own preference data, but this can lead to inaccuracies since the reward model shares weights with the target model, thereby amplifying inherent biases. To address these issues, we propose Anyprefer, a framework designed to synthesize high-quality preference data for aligning the target model. Anyprefer frames the data synthesis process as a cooperative two-player Markov Game, where the target model and the judge model collaborate together. Here, a series of external tools are introduced to assist the judge model in accurately rewarding the target model's responses, mitigating biases in the rewarding process. In addition, a feedback mechanism is introduced to optimize prompts for both models, enhancing collaboration and improving data quality. The synthesized data is compiled into a new preference dataset, Anyprefer-V1, consisting of 58K high-quality preference pairs. Extensive experiments show that Anyprefer significantly improves model alignment performance across four main applications, covering 21 datasets, achieving average improvements of 18.55% in five natural language generation datasets, 3.66% in nine vision-language understanding datasets, 30.05% in three medical image analysis datasets, and 16.00% in four visuo-motor control tasks.

Synergistic Weak-Strong Collaboration by Aligning Preferences

Current Large Language Models (LLMs) excel in general reasoning yet struggle with specialized tasks requiring proprietary or domain-specific knowledge. Fine-tuning large models for every niche application is often infeasible due to black-box constraints and high computational overhead. To address this, we propose a collaborative framework that pairs a specialized weak model with a general strong model. The weak model, tailored to specific domains, produces initial drafts and background information, while the strong model leverages its advanced reasoning to refine these drafts, extending LLMs' capabilities to critical yet specialized tasks. To optimize this collaboration, we introduce a collaborative feedback to fine-tunes the weak model, which quantifies the influence of the weak model's contributions in the collaboration procedure and establishes preference pairs to guide preference tuning of the weak model. We validate our framework through experiments on three domains. We find that the collaboration significantly outperforms each model alone by leveraging complementary strengths. Moreover, aligning the weak model with the collaborative preference further enhances overall performance.

AMPO: Active Multi-Preference Optimization

Multi-preference optimization enriches language-model alignment beyond pairwise preferences by contrasting entire sets of helpful and undesired responses, thereby enabling richer training signals for large language models. During self-play alignment, these models often produce numerous candidate answers per query, rendering it computationally infeasible to include all responses in the training objective. In this work, we propose $\textit{Active Multi-Preference Optimization}$ (AMPO), a novel approach that combines on-policy generation, a multi-preference group-contrastive loss, and active subset selection. Specifically, we score and embed large candidate pools of responses and then select a small, yet informative, subset that covers reward extremes and distinct semantic clusters for preference optimization. Our contrastive training scheme is capable of identifying not only the best and worst answers but also subtle, underexplored modes that are crucial for robust alignment. Theoretically, we provide guarantees for expected reward maximization using our active selection method, and empirically, AMPO achieves state-of-the-art results on $\textit{AlpacaEval}$ using Llama 8B.

Verifiable Format Control for Large Language Model Generations

Recent Large Language Models (LLMs) have demonstrated satisfying general instruction following ability. However, small LLMs with about 7B parameters still struggle fine-grained format following (e.g., JSON format), which seriously hinder the advancements of their applications. Most existing methods focus on benchmarking general instruction following while overlook how to improve the specific format following ability for small LLMs. Besides, these methods often rely on evaluations based on advanced LLMs (e.g., GPT-4), which can introduce the intrinsic bias of LLMs and be costly due to the API calls. In this paper, we first curate a fully verifiable format following dataset VFF. In contrast to existing works often adopting external LLMs for instruction-following validations, every sample of VFF can be easily validated with a Python function. Further, we propose to leverage this verifiable feature to synthesize massive data for progressively training small LLMs, in order to improve their format following abilities. Experimental results highlight the prevalent limitations in the format following capabilities of 7B level open-source LLMs and demonstrate the effectiveness of our method in enhancing this essential ability.

REFA: Reference Free Alignment for multi-preference optimization

We introduce REFA, a family of reference-free alignment methods that optimize over multiple user preferences while enforcing fine-grained length control. Our approach integrates deviation-based weighting to emphasize high-quality responses more strongly, length normalization to prevent trivial short-response solutions, and an EOS-probability regularizer to mitigate dataset-induced brevity biases. Theoretically, we show that under the Uncertainty Reduction with Sequence Length Assertion (URSLA), naive length normalization can still incentivize length-based shortcuts. By contrast, REFA corrects these subtle incentives, guiding models toward genuinely more informative and higher-quality outputs. Empirically, REFA sets a new state-of-the-art among reference-free alignment methods, producing richer responses aligned more closely with human preferences. Compared to a base supervised fine-tuned (SFT) mistral-7b model that achieves 8.4% length-controlled win rate (LC-WR) and 6.2% win rate (WR), our best REFA configuration attains 21.62% LC-WR and 19.87% WR on the AlpacaEval v2 benchmark. This represents a substantial improvement over both the strongest multi-preference baseline, InfoNCA (16.82% LC-WR, 10.44% WR), and the strongest reference-free baseline, SimPO (20.01% LC-WR, 17.65% WR)

SWEPO: Simultaneous Weighted Preference Optimization for Group Contrastive Alignment

We introduce Simultaneous Weighted Preference Optimization (SWEPO), a novel extension of Direct Preference Optimization (DPO) designed to accommodate multiple dynamically chosen positive and negative responses for each query. SWEPO employs a weighted group contrastive loss, assigning weights to responses based on their deviation from the mean reward score. This approach effectively prioritizes responses that are significantly better or worse than the average, enhancing optimization. Our theoretical analysis demonstrates that simultaneously considering multiple preferences reduces alignment bias, resulting in more robust alignment. Additionally, we provide insights into the training dynamics of our loss function and a related function, InfoNCA. Empirical validation on the UltraFeedback dataset establishes SWEPO as state-of-the-art, with superior performance in downstream evaluations using the AlpacaEval dataset.

Unveiling Context-Aware Criteria in Self-Assessing LLMs

The use of large language models (LLMs) as evaluators has garnered significant attention due to their potential to rival human-level evaluations in long-form response assessments. However, current LLM evaluators rely heavily on static, human-defined criteria, limiting their ability to generalize across diverse generative tasks and incorporate context-specific knowledge. In this paper, we propose a novel Self-Assessing LLM framework that integrates Context-Aware Criteria (SALC) with dynamic knowledge tailored to each evaluation instance. This instance-level knowledge enhances the LLM evaluator's performance by providing relevant and context-aware insights that pinpoint the important criteria specific to the current instance. Additionally, the proposed framework adapts seamlessly to various tasks without relying on predefined human criteria, offering a more flexible evaluation approach. Empirical evaluations demonstrate that our approach significantly outperforms existing baseline evaluation frameworks, yielding improvements on average 4.8% across a wide variety of datasets. Furthermore, by leveraging knowledge distillation techniques, we fine-tuned smaller language models for criteria generation and evaluation, achieving comparable or superior performance to larger models with much lower cost. Our method also exhibits a improvement in LC Win-Rate in AlpacaEval2 leaderboard up to a 12% when employed for preference data generation in Direct Preference Optimization (DPO), underscoring its efficacy as a robust and scalable evaluation framework.

CREAM: Consistency Regularized Self-Rewarding Language Models

Recent self-rewarding large language models (LLM) have successfully applied LLM-as-a-Judge to iteratively improve the alignment performance without the need of human annotations for preference data. These methods commonly utilize the same LLM to act as both the policy model (which generates responses) and the reward model (which scores and ranks those responses). The ranked responses are then used as preference pairs to train the LLM via direct alignment technologies (e.g. DPO). However, it is noteworthy that throughout this process, there is no guarantee of accuracy in the rewarding and ranking, which is critical for ensuring accurate rewards and high-quality preference data. Empirical results from relatively small LLMs (e.g., 7B parameters) also indicate that improvements from self-rewarding may diminish after several iterations in certain situations, which we hypothesize is due to accumulated bias in the reward system. This bias can lead to unreliable preference data for training the LLM. To address this issue, we first formulate and analyze the generalized iterative preference fine-tuning framework for self-rewarding language model. We then introduce the regularization to this generalized framework to mitigate the overconfident preference labeling in the self-rewarding process. Based on this theoretical insight, we propose a Consistency Regularized sElf-rewarding lAnguage Model (CREAM) that leverages the rewarding consistency across different iterations to regularize the self-rewarding training, helping the model to learn from more reliable preference data. With this explicit regularization, our empirical results demonstrate the superiority of CREAM in improving both reward consistency and alignment performance. The code is publicly available at https://github.com/Raibows/CREAM.