United States

LLM-based Multi-Agent Systems (MAS) have demonstrated remarkable capabilities in solving complex tasks. Central to MAS is the communication topology which governs how agents exchange information internally. Consequently, the security of communication topologies has attracted increasing attention. In this paper, we investigate a critical privacy risk: MAS communication topologies can be inferred under a restrictive black-box setting, exposing system vulnerabilities and posing significant intellectual property threats. To explore this risk, we propose \textbf{Communication Inference Attack (CIA)}, a novel attack that constructs new adversarial queries to induce intermediate agents&#39; reasoning outputs and models their semantic correlations through the proposed global bias disentanglement and LLM-guided weak supervision. Extensive experiments on MAS with optimized communication topologies demonstrate the effectiveness of CIA, achieving an average AUC of 0.87 and a peak AUC of up to 0.99, thereby revealing the substantial privacy risk in MAS. The source code is available at \url{https://github.com/aabbbcd/CIA}.

ACL 2026

CIA: Inferring the Communication Topology from LLM-based Multi-Agent Systems

### Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

Message from the General Chair: 
*It is my great pleasure and honor to welcome you to the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025), held in beautiful Vienna, Austria, from July 27 to August 1, 2025. ACL2025continues our field’s tradition of excellence in scholarship, innovation, and inclusivity, and I am deeply grateful to the many volunteers who have worked tirelessly to bring this event to life.* 
[Read more](https://drive.google.com/file/d/1GI_hvOpjswAuYdUTromfeDiPpCcqidwg/view?usp=sharing)

To access this event page, you need to log in with the **email address you registered with**. Access credentials will be sent to your email from Underline - subject line "Welcome to ACL 2025". Please be sure to check your spam email folder if you do not see an email confirmation right away.

Please log in

To access this event page, you need to log in with the **email address you registered with**. 

ACL 2025

Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

LLM-based Multi-Agent Systems (MAS) have demonstrated remarkable capabilities in solving complex tasks. Central to MAS is the communication topology which governs how agents exchange information internally. Consequently, the security of communication topologies has attracted increasing attention. In this paper, we investigate a critical privacy risk: MAS communication topologies can be inferred under a restrictive black-box setting, exposing system vulnerabilities and posing significant intellectual property threats. To explore this risk, we propose \textbf{Communication Inference Attack (CIA)}, a novel attack that constructs new adversarial queries to induce intermediate agents' reasoning outputs and models their semantic correlations through the proposed global bias disentanglement and LLM-guided weak supervision. Extensive experiments on MAS with optimized communication topologies demonstrate the effectiveness of CIA, achieving an average AUC of 0.87 and a peak AUC of up to 0.99, thereby revealing the substantial privacy risk in MAS. The source code is available at \url{https://github.com/aabbbcd/CIA}.

technical paper

It is my great pleasure and honor to welcome you to the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026), held in San Diego, California, USA, July 2–7, 2026. ACL 2026 continues our fields tradition of excellence in scholarship, innovation, and inclusivity, and I am deeply grateful to the many volunteers who have worked tirelessly to bring this event to life.

It is exciting to see the many developments in the field reflected at our conference, such as the advancement of large language models (born out of our community) into many application directions. This is not without challenges, partly due to unsolved problems, and partly due to misuse of the technology. All this is reflected well at ACL 2026. The conference also reflects that the field is not only about advancing technology, but also the science of fundamentally understanding language and how it is use by many different speaker communities. 
[Full Message from General Chair Philipp Koehn](https://drive.google.com/file/d/1QiJFOmMjvDgsDo3i1XzlQnImxe3RU_Cy/view?usp=sharing) 
<html><button style="display: inline-flex; align-items: center; justify-content: center; white-space: nowrap; border-radius: 9999px; font-weight: bold; background: #7c3aed; color: white; font-family: 'Space Grotesk', sans-serif; height: 40px; font-size: 16px; padding: 0 20px; border: none; cursor: pointer" onclick="window.open('https://drive.google.com/file/d/1QiJFOmMjvDgsDo3i1XzlQnImxe3RU_Cy/view?usp=sharing')">Conference Handbook</button></html>

To access this event page, you need to log in with the **email address you registered with**. Access credentials will be sent to your email from Underline - subject line "Welcome to ACL 2026". Please be sure to check your spam email folder if you do not see an email confirmation right away.

To access this event page, you are required to register.
Please complete your registration to continue.

We recommend reading [**the registration information**](https://2026.aclweb.org/registration/) first.

**Online Registration Form**: https://acl.swoogo.com/acl2026

Registration Required

The 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026) will take place in San Diego, California, from July 2 - 7, 2026.

Diffusion language models (DLMs) have emerged as a powerful non-autoregressive alternative to GPT-style sequential generation, but suffer from substantial computational overhead due to their iterative parallel denoising. Existing acceleration works cannot accurately detect semantically stabilized tokens and then skip computation, leading to sub-optimal speedup in practice. This paper presents the first systematic study of convergence dynamics in DLMs. Innovative observations include the misalignment between traditionally used scalar detection criterion and the semantic convergence, and the post-peak confidence score, that wastes denoising computation and degrades inference quality. To address these limitations, we propose Ada‑DLM, a semantic‑aware adaptive denoising framework that encodes the trajectory of scalar confidence scores into an evolution-aware feature vector and then clusters vectors proactively and adaptively identify semantically converged tokens. Furthermore, we incorporate system-level optimizations to maximize runtime efficiency. Experiments show that Ada‑DLM consistently outperforms the SOTA competitor, achieving up to 2x speedup and 19% quality improvement. That offers a practical path toward efficient high‑quality DLM deployment.

Towards Efficient and Effective Diffusion Language Model Inference via Semantic-Aware Adaptive Denoising

Computer-aided design (CAD) is crucial in prototyping complex 3D objects through precise geometric modeling. In practical design workflows, designers manually define assembly sequences for individual CAD parts, a process that is both time-consuming and expertise-intensive. To address this challenge, we formulate CAD assembly as a parametric action prediction task: given a reference design image and disassembled parts, the model predicts 6-DoF transformations (\ie, actions) to progressively assemble each part. This paradigm enables multimodal large language models (MLLMs) to solve the task through autoregressive action generation. While recent MLLMs demonstrate promising spatial reasoning, they struggle with fine-grained geometric structure understanding and physical collision avoidance during assembly. In this paper, we propose \textsc{CADMate}, an MLLM-based framework for sequential CAD assembly action generation. Our training strategy comprises three stages: (i) CAD domain adaptation for spatial geometry and position understanding, (ii) supervised fine-tuning with geometric chain-of-thought (CoT) reasoning for action generation, and (iii) reinforcement learning with spatial-physical rewards jointly optimize spatial accuracy and collision avoidance. Additionally, we also construct \textit{CADBuilder} dataset, comprising over 45\textit{K} CAD assemblies with annotated action sequences. Our experiments demonstrate that \textsc{CADMate} significantly outperforms existing prominent MLLMs (\eg, GPT-5), showing great potential in design applications.

CADMate: Generating CAD Assembly Plan with Geometric Chain-of-Thought and Spatial Physical Rewards

Group Relative Policy Optimization (GRPO) enhances LLM reasoning but often induces overconfidence, where incorrect responses yield lower perplexity than correct ones, degrading relative calibration as described by the Area Under the Curve (AUC). Existing approaches either yield limited improvements in calibration or sacrifice gains in reasoning accuracy. We first prove that this degradation in GRPO-style algorithms stems from their uncertainty-agnostic advantage estimation, which inevitably misaligns optimization gradients with calibration. This leads to improved accuracy at the expense of degraded calibration. We then propose Calibration-Aware Policy Optimization (CAPO). It adopts a logistic AUC surrogate loss that is theoretically consistent and admits regret bound, enabling uncertainty-aware advantage estimation. By further incorporating a noise masking mechanism, CAPO achieves stable learning dynamics that jointly optimize calibration and accuracy. Experiments on multiple mathematical reasoning benchmarks show that CAPO-1.5B significantly improves calibration by up to 15% while achieving accuracy comparable to or better than GRPO, and further boosts accuracy on downstream inference-time scaling tasks by up to 5%. Moreover, when allowed to abstain under low-confidence conditions, CAPO achieves a Pareto-optimal precision–coverage trade-off, highlighting its practical value for hallucination mitigation.

Calibration-Aware Policy Optimization for Reasoning LLMs

Low-Rank Adaptation (LoRA) enables parameter-efficient fine-tuning of Large Language Models (LLMs), and recent Mixture-of-Experts (MoE) extensions further enhance flexibility by dynamically combining multiple LoRA experts. However, existing MoE-augmented LoRA methods assume that experts operate independently, often leading to unstable routing, expert dominance. In this paper, we propose TalkLoRA, a communication-aware MoELoRA framework that relaxes this independence assumption by introducing expert-level communication prior to routing. TalkLoRA equips low-rank experts with a lightweight Talking Module that enables controlled information exchange across expert subspaces, producing a more robust global signal for routing. Theoretically, we show that expert communication smooths routing dynamics by mitigating perturbation amplification while strictly generalizing existing MoELoRA architectures. Empirically, TalkLoRA consistently outperforms vanilla LoRA and MoELoRA across diverse language understanding and generation tasks, achieving higher parameter efficiency and more balanced expert routing under comparable parameter budgets. These results highlight structured expert communication as a principled and effective enhancement for MoE-based parameter-efficient adaptation.

TalkLoRA: Communication-Aware Mixture of Low-Rank Adaptation for Large Language Models

While recent self-training approaches have reduced reliance on human-labeled data for aligning LLMs, they still face critical limitations: (i) sensitivity to synthetic data quality, leading to instability and bias amplification in iterative training; (ii) ineffective optimization due to a diminishing gap between positive and negative responses over successive training iterations. In this paper, we propose Team-based self-Play with dual Adaptive Weighting (TPAW), a novel self-play algorithm designed to improve alignment in a fully self-supervised setting. TPAW adopts a team-based framework in which the current policy model both collaborates with and competes against historical checkpoints, promoting more stable and efficient optimization. To further enhance learning, we design two adaptive weighting mechanisms: (i) a response reweighting scheme that adjusts the importance of target responses, and (ii) a player weighting strategy that dynamically modulates each team member’s contribution during training. Initialized from a SFT model, TPAW iteratively refines alignment without requiring additional human supervision. Experimental results demonstrate that TPAW consistently outperforms existing baselines across various base models and LLM benchmarks.

Team-Based Self-Play With Dual Adaptive Weighting for Fine-Tuning LLMs

Question answering (QA) with reference texts is a classic application scenario for large language models (LLMs), where high standards for the credibility and traceability of generated answers are crucial. Many existing approaches focus on generating multi-level citations linked to specific references within the answer, making it verifiable and trustworthy. However, they often overlook key challenges such as citation granularity, the awareness of unknown information, and the adoption of effective training strategies. In this paper, we introduce Knowledge-informed Citation (KFC), which addresses these issues through a novel data construction pipeline, a new benchmark, and an innovative training strategy. With approximately 42K samples spanning 19 distinct domains, KFC includes both traditional citations referencing known entity-level information and specialized citations referring to unknown knowledge in the given question. This structure provides a more granular approach to citations, guiding the model to recognize and explicitly indicate unknown information, thus enhancing the quality and credibility of the response. Additionally, we propose a self-correction paradigm, Self-KFC, designed to fine-tune LLMs by refining poorly cited answers into more accurate ones, making it particularly suitable for citation-dependent scenarios. We present comprehensive experimental results to demonstrate the effectiveness and generalization of Self-KFC on the KFC benchmark.

Know the Known and the Unknown: Reasonable Answer Generation with Knowledge-Informed Citations

While Large Language Models (LLMs) have significantly advanced the fluency of Emotional Support Conversation (ESC) systems, current research predominantly focuses on engineering increasingly complex architectures—from intricate reasoning chains to multi-agent collaborations. While these advancements (e.g., CoT) offer semantic traces of reasoning, they remain mechanistically opaque, obscuring the fundamental causal mechanisms between dialogue features and effective empathic strategies, leading to poor interpretability and susceptibility to distribution shifts in offline learning. To address these limitations, we propose a novel framework \textbf{Causal-ESC}. Departing from conventional paradigms that directly utilize raw dialogue history as input, our approach introduces Doubly Robust (DR) learning to explicitly model the causal effect of utterance features on strategy selection, effectively mitigating the biases and counterfactual unobservability inherent in offline datasets. We further integrate an LLM-based stylized rewriting mechanism to translate these rigorously learned causal strategies into natural, context-consistent responses. Comprehensive experiments, supported by statistical verification (e.g., Outcome $R^2$) and human-like evaluation, demonstrate that our framework not only significantly outperforms state-of-the-art baselines in empathy and helpfulness but also provides a theoretically grounded, interpretable solution to the mechanistic interpretability dilemma in affective computing.

Causal-ESC: Reliable Policy Learning for Emotional Support Conversation via Causal Inference

Games offer a compelling paradigm for developing general reasoning capabilities in language models, as they naturally demand strategic planning, probabilistic inference, and adaptive decision-making. However, existing self-play approaches rely solely on terminal game outcomes, providing no mechanism to distinguish transferable reasoning patterns from game-specific heuristics. We present STRATAGEM, which addresses two fundamental barriers to reasoning transfer: domain specificity, where learned patterns remain anchored in game semantics, and contextual stasis, where static game contexts fail to cultivate progressive reasoning. STRATAGEM selectively reinforces trajectories exhibiting abstract, domain-agnostic reasoning through a Reasoning Transferability Coefficient, while incentivizing adaptive reasoning development via a Reasoning Evolution Reward. Experiments across mathematical reasoning, general reasoning, and code generation benchmarks demonstrate substantial improvements, with particularly strong gains on competition-level mathematics where multi-step reasoning is critical. Ablation studies and human evaluation confirm that both components contribute to transferable reasoning.

Stratagem: Learning Transferable Reasoning via Trajectory-Modulated Game Self-Play

Effective memory management is essential for large language model agents to navigate long-horizon tasks. Recent research has explored using Reinforcement Learning to develop specialized memory manager agents. However, existing approaches rely on final task performance as the primary reward, which results in severe reward sparsity and ineffective credit assignment, providing insufficient guidance for individual memory operations. To this end, we propose Fine-Mem, a unified framework designed for fine-grained feedback alignment. First, we introduce a Chunk-level Step Reward to provide immediate step-level supervision via auxiliary chunk-specific question answering tasks. Second, we devise Evidence-Anchored Reward Attribution to redistribute global rewards by anchoring credit to key memory operations, based on the specific memory items utilized as evidence in reasoning. Together, these components enable stable policy optimization and align local memory operations with the long-term utility of memory. Experiments on Memalpha and MemoryAgentBench demonstrate that Fine-Mem consistently outperforms strong baselines, achieving superior success rates across various sub-tasks. Further analysis reveals its adaptability and strong generalization capabilities across diverse model configurations and backbones

Fine-Mem: Fine-Grained Feedback Alignment for Long-Horizon Memory Management

Long-context summarization is pivotal for extracting core insights from extensive documents. While Large Language Models (LLMs) show remarkable capabilities, they frequently encounter attention dilution and hallucination with lengthy inputs. Retrieval-Augmented Generation (RAG) partially mitigates this, but conventional RAG relies on shallow similarity retrieval of fragmented chunks, failing to capture high-level thematic structures and long-range dependencies. Although graph-based RAG approaches have emerged to address these structural limitations, existing solutions, such as Graph of Records (GoR), critically suffer from a fundamental flaw: they paradoxically re-introduce hallucinations by constructing graphs based on unreliable, LLM-generated responses. To overcome these challenges, we introduce Hierarchical Graph of Evidence} (HiGoE) (Code link https://github.com/tkw123/HiGOE). HiGoE redefines the retrieval process by replacing unreliable chunk-based methods with a filtered proposition–evidence graph, ensuring verifiable fact grounding and substantially reducing hallucination. Moreover, HiGoE leverages Personalized PageRank (PPR) to cluster related nodes into thematic hierarchies, thereby restoring global document structure and effectively mitigating attention dilution. To model complex, multi-level relations beyond mere shallow similarity, we develop an Enhanced Graph Attention Network. Experiments show HiGoE consistently surpasses baselines in quality and efficiency.

Downloads

Next from ACL 2026

Towards Efficient and Effective Diffusion Language Model Inference via Semantic-Aware Adaptive Denoising

Similar lecture

G-Safeguard: A Topology-Guided Security Lens and Treatment on LLM-based Multi-agent Systems

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES