United States

Recent advances in Reinforcement Learning with Verifiable Rewards (RLVR) have demonstrated significant potential in single-turn reasoning tasks. With the paradigm shift toward self-evolving agentic learning, models are increasingly expected to learn from trajectories by synthesizing tools or accumulating explicit experiences. However, prevailing methods typically rely on large-scale LLMs or multi-agent frameworks, which hinder their deployment in resource-constrained environments. The inherent sparsity of outcome-based rewards also poses a substantial challenge, as agents typically receive feedback only upon task completion. To address these limitations, we introduce a Tool-Memory based self-evolving agentic framework SEARL. Unlike approaches that directly utilize interaction experiences, our method constructs a structured experience memory that integrates planning with execution. This provides a novel form of state abstraction that facilitates the aggregation of actions within functionally analogous contexts, such as tool reuse. Consequently, agents not only extract explicit knowledge from historical data but also leverage inter-trajectory correlations to densify reward signals. We evaluate our framework on knowledge reasoning and complex search tasks, demonstrating its effectiveness in achieving more practical and efficient agentic learning.

ACL 2026

SEARL: Joint Optimization of Policy and Tool Graph Memory for Self-Evolving Agents

### 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)

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.

Structural understanding of natural language requires explicit recovery of internal meaning structures (entities, facts, nested relations), yet current structural-analytic tasks are fragmented by inconsistent task requirements across datasets. We investigate the problem of robust cross-task structural understanding under heterogeneous requirements across structural-analytic tasks and outline a perspective called Analytic NLP in which tasks can be reformulated into a representation-then-decision paradigm. In this paper, we suggest a solution for the representation layer, called Lingua-Graph, which explicitly captures entities, facts, and relations. By representing predictions as explicit graphs with labeled nodes and edges, Lingua-Graph also improves interpretability, enabling transparent inspection and error analysis of intermediate meaning structures. We construct a labeled Lingua-Graph dataset and train a baseline parser. Experiments show that Lingua-Graph provides substantially higher entity-structure hostability than alternative representations on average, and OpenIE systems based on Lingua-Graph achieve superior performance on three benchmarks, demonstrating that better intermediate structures translate into downstream gains. The data, code and the trained model are publicly released at \url{https://github.com/rudaoshi/Lingua}.

Lingua-Graph: A Unified Representation of Cross-Task Common Substructures for Analytic Language Processing

Large Reasoning Models (LRMs) excel at complex problem-solving but frequently overlook specific instruction constraints. Existing alignment methods struggle to balance general reasoning with instruction-following (IF), hindered by dependency on teacher models, reward hacking, and reasoning-answer inconsistencies. We propose PARIF, a two-stage curriculum learning framework based on Reinforcement Learning from Verifiable Rewards (RLVR) to enhance both IF and general reasoning capabilities. The framework employs a correctness proxy across different stages to mitigate reward hacking. Stage I employs a dynamic weighting strategy simultaneously to optimize the model's reasoning paradigm regarding constraints. Stage II introduces Decoupled-GRPO, which builds upon the first stage to enhance the logical consistency between the reasoning process and the final answer, enabling the model to better leverage its optimized reasoning paradigm. To support the framework, we curate 26,000 high-quality instructions featuring diverse constraints. Extensive experiments demonstrate PARIF's effectiveness: our 7B model achieves a remarkable 21.25% relative average improvement to the original model across six representative IF tasks, while our 8B model outperforms leading models like DeepSeek-V3 on these IF tasks, effectively pushing the Pareto frontier of instruction following and reasoning for models of comparable scale. We open-source our code and models to facilitate future research.

PARIF: Pushing the Pareto Frontier of Instruction Following and Reasoning with Curriculum Reinforcement Learning

Large Language Models (LLMs) and Large Vision-Language Models (LVLMs) demonstrate strong reasoning capabilities, yet their performance in English significantly outperforms that in low-resource languages, raising fairness concerns in multilingual applications. Existing approaches either rely on costly multilingual training or employ prompting with external translation tools, both of which are resource-intensive and sensitive to translation quality. To address these limitations, we propose a training-free inference-time method to enhance Multilingual Reasoning capabilities via Representation Engineering (MRRE) without using any additional training data or tools. MRRE sequentially injects two precomputed vectors at specific layers during inference processing: cross-lingual reasoning enhancement vectors, which steer non-English reasoning representations toward English space to unlock multilingual reasoning, and target-language output anchoring vectors, which restore the distribution of the target language to preserve input–output language consistency. Comprehensive experiments across six advanced LLMs and LVLMs on four reasoning benchmarks demonstrate that MRRE consistently enhances non-English reasoning by an average gain of 5.48% and up to 7.54% in low-resource languages (e.g., Thai and Swahili), while improving input-output language consistency by 3.78%.

Unlocking Multilingual Reasoning Capability of LLMs and LVLMs through Representation Engineering

Large Vision-Language Models (LVLMs) have achieved remarkable performance on diverse vision-language tasks. However, LVLMs still suffer from hallucinations, generating text that contradicts the visual input. Existing research has primarily focused on mitigating object hallucinations, but often overlooks more complex relation hallucinations, particularly action relations involving interactions between objects. In this study, we empirically observe that the primary cause of action-relation hallucinations in LVLMs is the insufficient attention allocated to visual information. Thus, we propose a framework to locate action-relevant image regions and enhance the LVLM's attention to those regions. Specifically, we define the Action-Relation Sensitivity (ARS) score to identify attention heads that are most sensitive to action-relation changes, thereby localizing action-relevant image regions that contain key visual cues. Then, we propose the Relation-aware Visual Enhancement (RVE) method to enhance the LVLM's attention to these action-relevant image regions. Extensive experiments demonstrate that, compared to existing baselines, our method achieves superior performance in mitigating action-relation hallucinations with negligible additional inference cost. Furthermore, it effectively generalizes to spatial-relation hallucinations and object hallucinations.

Mitigating Action-Relation Hallucinations in LVLMs via Relation-aware Visual Enhancement

Many real-world applications require generating a chronological report from an evolving document stream; Timeline Summarization (TLS) provides a standard testbed for this setting. While large language models (LLMs) improve event synthesis, most LLM-based TLS systems remain monolithic: they repeatedly process overlapping evidence and often mirror the corpus' bursty reporting patterns, producing redundant timelines with temporal/topical imbalance and high cost. We propose **MAS-TLS**, a multi-agent framework that casts TLS as a *newsroom-like* collaboration. A master editor steers balanced coverage by allocating system-visible evidence with a coverage--diversity objective; specialist reporter agents independently draft time-anchored, evidence-grounded events while cross-reviewing to limit redundancy; an adjudication round reconciles competing drafts and consolidates duplicates into a global timeline; and a non-stationary Bayesian controller adaptively staffs agents under token/time budgets. Experiments on three benchmarks show that MAS-TLS improves semantic coverage and temporal grounding while substantially reducing token usage and latency.

Agent Newsroom: Efficient Chronological Report Generation via Dynamic Multi-Agent Collaboration

Recent advances in large language models (LLMs) have enabled increasingly capable web agents, yet training such agents still relies on high-quality interaction trajectories that are difficult to obtain at scale. We identify two key challenges: (1) Infrastructure Overhead, where network instability and website access restrictions limit data collection scalability; and (2) Constrained Exploration, where irreversible state transitions preclude tree-based search and thus limit trajectory diversity. To address these challenges, we introduce WebSynthesis, a framework for scalable trajectory synthesis. WebSynthesis employs an LLM-based World Model to simulate state transitions without network dependencies, and integrates Monte Carlo Tree Search to enable reversible exploration over the simulated state space. Experiments on WebArena, WebVoyager, and Mind2Web-Online demonstrate that agents trained exclusively on synthesized trajectories outperform those trained on real-world data, providing a viable alternative to costly real-world data collection.

WebSynthesis: World Model-Guided Monte Carlo Tree Search for Efficient WebAgent Trajectory Synthesis

Low-Rank Adaptation (LoRA) has emerged as a prominent solution to mitigate the communication and computation costs in federated fine-tuning of Large Language Models (LLMs). However, we observe that even within low-rank adapters, a substantial portion of parameters manifest negligible updates during federated training, leading to redundant communication and wasted local computation. To address this, we propose \textbf{GMFL}, a \textbf{plug-and-play} layer freezing mechanism designed to \textbf{seamlessly integrate} with existing federated fine-tuning frameworks. Specifically, the server monitors the global update magnitude of each LoRA layer to dynamically generate freezing masks. These masks are updated periodically with a fixed freezing rate, ensuring stable convergence by robustly identifying ``saturated'' layers. Theoretical analysis confirms the convergence of GMFL, where the freezing mechanism yields a bounded error that scales with client heterogeneity. Extensive experiments across multiple tasks (GLUE, Commonsense Reasoning, Math Reasoning and General Generation) demonstrate that GMFL reduces communication overhead and lowers computational costs while preserving the performance of the underlying federated fine-tuning methods. Our work provides a practical, versatile solution for deploying large-scale federated LLM fine-tuning in resource-constrained environments. Our code is available at: \url{https://github.com/tunx-cyber/GMFL}.

GMFL: Efficient Global Masking for Federated LLM Fine-tuning

Large language models (LLMs) face significant challenges in processing long contexts due to the linear growth of the key-value (KV) cache and quadratic complexity of self-attention. Existing approaches address these bottlenecks separately: Multi-head Latent Attention (MLA) reduces the KV cache by projecting tokens into a low-dimensional latent space, while sparse attention reduces computation. However, sparse methods cannot operate natively on MLA’s compressed latent structure, missing opportunities for joint optimization. In this paper, we propose Latent-Condensed Attention (LCA), which directly condenses context within MLA’s latent space, where the representation is disentangled into semantic latent vectors and positional keys. LCA separately aggregates semantic vectors via query-aware pooling and preserves positional keys via anchor selection. This approach jointly reduces both computational cost and KV cache without adding parameters. Beyond MLA, LCA’s design is architecture-agnostic and readily extends to other attention mechanisms such as GQA. Theoretically, we prove a length-independent error bound. Experiments show LCA achieves up to **2.5×** prefilling speedup and **90%** KV cache reduction at 128K context while maintaining competitive performance.

Latent-Condensed Transformer for Efficient Long Context Modeling

Existing knowledge graph completion research is gradually shifting from representing logical semantics of static facts to modeling evolving semantics of temporal facts, yet lacks collaborative modeling of both within a unified framework. To this end, we use concept of snapshots to decompose fact features into two complementary mechanisms: (a) intra-snapshot semantic coupling, where entities and relations exhibit snapshot-specific meanings through multidimensional interactions; (b) trans-snapshot evolutionary synergy, where relations between entities evolve across snapshots and manifest varying states. These snapshot mechanisms jointly reveal underlying logic of facts. To track them, we propose TeCES, a framework for high-fidelity modeling of evolving snapshots. TeCES embeds facts into a 2-grade geometric algebra (GA) system to capture complex semantics via multilevel structures. Temporal information is attached to each entity for mapping into snapshot spaces, while relations and timestamps are reconfigured into composite GA representations. Geometric products enable multidimensional interactions, revealing relation state changes over time. Lastly, the head entity at each snapshot combines with fused temporal-relational representation via geometric product to approximate the target tail entity at multiple levels. Overall, TeCES supports joint modeling of evolving snapshots within a lightweight GA system and significantly outperforms SOTA models on six benchmarks.

TeCES: Collaborative Geometric Knowledge Representation Framework under Evolving Fact Snapshots

Temporal Knowledge Graph Question Answering (TKGQA) is inherently challenging, as it requires sophisticated reasoning over dynamic facts with multi-hop dependencies and complex temporal constraints. Existing methods rely on fixed workflows and expensive closed-source APIs, limiting flexibility and scalability. We propose **Temp-R1**, the first autonomous end-to-end agent for TKGQA trained through reinforcement learning. To address cognitive overload in single-action reasoning, we expand the action space with specialized internal actions alongside external action. To prevent shortcut learning on simple questions, we introduce reverse curriculum learning that trains on difficult questions first, forcing the development of sophisticated reasoning before transferring to easier cases. Our 8B-parameter Temp-R1 achieves state-of-the-art performance on MultiTQ and TimelineKGQA, improving 19.8\% over strong baselines on complex questions. Our work establishes a new paradigm for autonomous temporal reasoning agents. The code is available at \url{https://github.com/zjukg/Temp-R1}.

Downloads

Next from ACL 2026

Lingua-Graph: A Unified Representation of Cross-Task Common Substructures for Analytic Language Processing

Similar lecture

Agentic Reasoning: A Streamlined Framework for Enhancing LLM Reasoning with Agentic Tools