United States

Agentic search requires large language models (LLMs) to perform multi-step search to solve complex information-seeking tasks, imposing unique challenges on their reasoning capabilities. However, what constitutes effective reasoning for agentic search and how it can be learned remains unclear. In this work, we first investigate the reasoning behaviors that enable success in agentic search. By comparing successful and failed trajectories via an LLM-based analysis pipeline, we identify four beneficial behaviors: Information Verification, Authority Evaluation, Adaptive Search, and Error Recovery. Building on this, we propose Behavior Priming, a training approach that equips agentic search models with these reasoning behaviors before reinforcement learning (RL). Specifically, it collects trajectories with the identified behaviors for supervised fine-tuning (SFT), and then applies standard RL to further improve task performance. Experiments on Qwen3-1.7B and Llama3.2-3B-Instruct show that Behavior Priming yields relative improvements over direct RL by 37.2% on three web benchmarks and 6.2% on seven multi-hop QA benchmarks, and outperforms the SFT-then-RL baseline using outcome-correct trajectories for fine-tuning. Crucially, we show that these reasoning behaviors matter more than outcome correctness in the priming stage prior to RL. Further analysis reveals that Behavior Priming enhances exploration (pass@8) and test-time scaling (search step number), providing a robust foundation for RL.

ACL 2026

Beneficial Reasoning Behaviors in Agentic Search and Effective Training Methods to Obtain Them

## Welcome!
"I am excited to welcome you to this year’s edition of the Conference on Empirical Methods in Natural Language Processing! Importantly, it marks the 30th edition of EMNLP. With over 8,000 submissions, more than 3,000 accepted papers, and thousands of attendees, we have come a long way from that first
workshop, which had 14 accepted papers. As the field looks ahead, Suzhou is the fitting location for celebrating this milestone: rooted in a long literary tradition, yet modern and forward-looking, and home to a large share of the NLP community." 

*Message from the General Chair, Dirk Hovy*

EMNLP 2025

Celebrate 30 Years of EMNLP! 
EMNLP 2025 will be held in Suzhou, China from November 5th to November 9th, 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.

Aligning Large Vision-Language Models (LVLMs) to mitigate hallucinations typically relies on high-quality preference data. However, in self-supervised settings, standard binary preference optimization (e.g., DPO) suffers from noisy supervision and semantic ambiguity, as automatically generated chosen responses are not guaranteed to be superior to rejected ones. In this work, we propose \textbf{Trident}, a fully self-supervised framework that ensures robust alignment via a structured triplet paradigm. Trident autonomously constructs reliable preference triplets—comprising semantically enriched (chosen), degraded (rejected), and neutral (anchor) responses—through automated visual perturbations and self-summarization. We further introduce Trident Preference Regularization (TPR), a novel objective that utilizes an adaptive margin to enforce semantic separation between the triplet components while preventing deviation from the pretrained distribution. Despite requiring no human annotations or external reward models, Trident consistently outperforms state-of-the-art RLHF and RLAIF baselines. For instance, on LLaVA-1.5-7B, it reduces the hallucination rate on AMBER to 11.3% and achieves 95.70% precision on POPE using only 4k self-generated triplets and a single epoch. This validates structured triplet supervision as a scalable paradigm for robust self-supervised alignment.

Trident: Self-Supervised Preference Alignment via Triplet Regularization

Despite significant advances in Large Reasoning Models (LRMs) driven by reinforcement learning with verifiable rewards (RLVR), this paradigm is fundamentally limited in specialized or novel domains where such supervision is prohibitively expensive or unavailable, posing a key challenge for test-time adaptation. 
While existing test-time methods offer a potential solution, they are constrained by learning from static query sets, risking overfitting to textual patterns. 
To address this gap, we introduce Test-Time Variational Synthesis (TTVS), a novel framework that enables LRMs to self-evolve by dynamically augmenting the training stream from unlabeled test queries. TTVS comprises two synergistic modules: (1) Online Variational Synthesis, which transforms static test queries into a dynamic stream of diverse, semantically-equivalent variations, enforcing the model to learn underlying problem logic rather than superficial patterns; (2) Test-time Hybrid Exploration, which balances accuracy-driven exploitation with consistency-driven exploration across synthetic variants. Extensive experiments show TTVS yields superior performance across eight model architectures. Notably, using only unlabeled test-time data, TTVS not only surpasses other test-time adaptation methods but also outperforms state-of-the-art supervised RL-based techniques trained on vast, high-quality labeled data.

TTVS: Boosting Self-Exploring Reinforcement Learning via Test-time Variational Synthesis

Large Audio Language Models (LALMs) employing the Chain-of-Thought paradigm have demonstrated remarkable reasoning capabilities. Though different problems naturally require varying depths of reasoning, existing methods often determine whether to perform reasoning, lacking fine-grained mechanisms to adapt reasoning length to problem complexity. As a result, LALMs often adopt a one-size-fits-all reasoning strategy, leading to redundant overthinking for simple tasks and insufficient reasoning for complex ones. In this paper, we conduct an in-depth analysis of LALM reasoning behavior and argue that effective and efficient reasoning should be adaptively aligned with task difficulty. To this end, we propose a difficulty-adaptive reasoning method for LALMs. Specifically, we introduce a reward function that dynamically links reasoning length to the model's perceived problem difficulty, encouraging shorter reasoning for easy tasks and longer reasoning for more complex ones. Extensive experiments on three datasets demonstrate that our method consistently improves performance while reducing average reasoning length by at least 50\%, achieving higher efficiency without sacrificing accuracy.

Think Smart, Not Hard: Difficulty Adaptive Reasoning for Large Audio Language Models

While scaling test-time compute can substantially improve model performance, existing approaches either rely on static compute allocation or sample from fixed generation distributions.
In this work, we introduce a test-time compute allocation framework that jointly adapts where computation is spent and how generation is performed. 
Our method begins with a warm-up phase that identifies easy queries and assembles an initial pool of question-response pairs from the test set itself. An adaptive phase then concentrates further computation on unresolved queries while reshaping their generation distributions through evolving in-context demonstrations---conditioning each generation on successful responses from semantically related queries rather than resampling from a fixed distribution.
Experiments across math, coding, and reasoning benchmarks demonstrate that our approach consistently outperforms existing baselines while consuming substantially less inference-time compute.

Adaptive Test-Time Compute Allocation with Evolving In-Context Demonstrations

Scaling training compute, measured in FLOPs, has long been shown to improve the accuracy of large language models, yet training remains resource-intensive. Prior work shows that increasing test-time compute (TTC)—for example through iterative sampling—can allow smaller models to rival or surpass much larger ones at lower overall cost. We introduce TTC-aware training, where an intermediate checkpoint and a corresponding TTC configuration can together match or exceed the accuracy of a fully trained model while requiring substantially fewer training FLOPs. Building on this insight, we propose an early stopping algorithm that jointly selects a checkpoint and TTC configuration to minimize training compute without sacrificing accuracy. To make this practical, we develop an efficient TTC evaluation method that avoids exhaustive search, and we formalize a break-even bound that identifies when increased inference compute compensates for reduced training compute. Experiments demonstrate up to 92\% reductions in training FLOPs while maintaining and sometimes remarkably improving accuracy. These results highlight a new perspective for balancing training and inference compute in model development, enabling faster deployment cycles and more frequent model refreshes.

FLOP-Efficient Training: Early Stopping Based on Test-Time Compute Awareness

Flow-matching generative models have created significant milestones in text-to-audio generation, powered by scalable training with increased data, computational resources, and model size, while their scalable inference remains less explored. In this work, we propose MaskAudioFlow, a continuous flow-matching transformer with masked generative modeling designed for scaling text-to-audio inference-time prediction. Specifically, MaskAudioFlow 1) masks spans of audio frames in training and approximates the continuous velocity vector field with flow-matching objective, and 2) performs inference via masked prediction, where we mask out generation and re-predict them through iterative decoding. To reduce the gap between generation and human preferences, we fine-tune MaskAudioFlow using reward signals from text-audio correspondence and perceptual aesthetics. Experimental results demonstrate that MaskAudioFlow achieves state-of-the-art performance in text-to-audio generation, effectively scaling inference-time computation through iterative masked prediction. Moreover, the preference-tuned model demonstrates superior text-audio alignment faithfulness and enhanced perceptual aesthetics. Audio samples are available at https://MaskAudio.github.io

Masked Text-to-Audio Flow-Matching and Reward Feedback Optimization

Explainability has become a crucial concern in today's world, aiming to enhance transparency in machine learning and deep learning models. Information retrieval is no exception to this trend. In existing literature on explainability of information retrieval, the emphasis has predominantly been on illustrating the concept of relevance concerning a retrieval model. The questions addressed include why a document is relevant to a query, why one document exhibits higher relevance than another, or why a specific set of documents is deemed relevant for a query. However, limited attention has been given to understanding why a particular document is not favored (e.g., not within top-K) with respect to a query and a retrieval model. In an effort to address this gap, our work focuses on the question of what terms need to be added within a document to improve its ranking. This, in turn, answers the question of which words in the document played a role in not being favored by a retrieval model for a particular query. We use a counterfactual framework to solve the above-mentioned research problem. Our experiments show the effectiveness of our proposed approach in predicting counterfactuals for both statistical (e.g. BM25) and deep-learning-based models (e.g. DRMM, DSSM, ColBERT, MonoT5).

A Counterfactual Explanation Framework for Retrieval Models

Group Relative Policy Optimization (GRPO) has demonstrated wide adoption in the post-training of Large Language Models (LLMs). In GRPO, prompts are answered by the model and preferred behaviour is learnt via reinforcement learning. Owing to the small communication volume, GRPO is inherently suitable for decentralised training as the prompts can be concurrently answered by multiple nodes and these completions are exchanged in the form of strings. In this work, we explore the robustness of decentralised GRPO by presenting the first adversarial attacks and countermeasures. We present a diverse set of attacks where malicious nodes poison benign models by sharing their poisoned completions. We demonstrate these attacks on math and coding tasks and show that an adversary can achieve attack success rates of up to (100%) in as few as 50 iterations. Moreover, to mitigate the attacks, we propose two defense mechanisms that check logit probabilities of completions or utilize an LLM judge to filter completions. The defenses prevent all but the DoS attack that causes unnecessarily lengthy but conceptually correct completions. The code of both attacks and defenses can be found at: https://github.com/gensyn-ai/HTTT.

Hail to the Thief: Exploring Attacks and Defenses in Decentralised GRPO

Evaluating software engineering capabilities has become a core component of modern large language models (LLMs); however, the key bottleneck hindering further scaling lies not in the scarcity of high-quality solutions, but in the lack of high-quality test suites. Test suites are indispensable both for synthesizing program repair trajectories and for providing precise feedback signals in reinforcement learning. Unfortunately, due to the high cost and difficulty of annotation, high-quality test suites have long been hard to obtain, while those automatically generated by LLMs tend to be superficial and lack sufficient discriminative power. As a first step toward constructing high-quality test suites, we introduce SWE-Mutation, a benchmark for evaluating LLM-generated test suites. The benchmark characterizes test suites by introducing systematically mutated solutions that attempt to ``fool'' the test suites and pass validation. We further propose an agentic, language-agnostic framework for automatically generating complex mutants. Our benchmark consists of 2,636 mutated variants derived from 800 original instances and includes a multilingual subset spanning nine programming languages. Experiments on seven LLMs reveal that even DeepSeek-V3.1 achieves only 10.20\% verification and 36.15\% detection rates, highlighting the inadequacy of current LLMs. Additionally, our agentic mutation strategy enhances realism, reducing average detection rates from 71.04\% to 39.81\% compared to conventional methods. These findings expose persistent deficiencies in the ability of current LLMs to generate reliable and discriminative test suites.

SWE-Mutation: Can LLMs Generate Reliable Test Suites in Software Engineering?

We study how well LLMs can determine whether two programs are functionally equivalent. This is an important problem because benchmarking code equivalence helps assess LLM capability in tasks such as code rewriting and translation. To this end, we introduce CETBench — Code Equivalence with Transformations Benchmark — built from a repository of programs that may solve the same or different tasks. Each dataset instance is created by sampling a program pair and applying a random sequence of predefined code transformations, yielding either equivalent or non-equivalent pairs. Our analysis shows that even simple transformations cause a significant performance drop in state-of-the-art LLMs on code-equivalence checking. These challenges are further amplified in the cross-lingual setting when comparing programs written in different languages. To remedy this, we present a simple fine-tuning-based approach to boost LLM performance on the transformed pairs of programs. Our approach for dataset generation is generic, supporting cross-lingual equivalence checking, the generation of program pairs with varying difficulty levels, and the application of diverse transformations. In our experiments, we perform ablations over the difficulty level of original programs, as well as the kind of transformations used in generating pairs for equivalence checking. Our analysis presents deep insights into the working of LLMs for the task of code-equivalence, and points to the fact that they may still be far from what could be termed as a semantic understanding of the underlying code.

Downloads

Next from ACL 2026

Trident: Self-Supervised Preference Alignment via Triplet Regularization

Similar lecture

Search Wisely: Mitigating Sub-optimal Agentic Searches By Reducing Uncertainty