United States

Test-time compute (TTC) scaling has emerged as a powerful paradigm for improving large language model (LLM) reasoning by allocating additional compute during inference, e.g., via multi-sample generation and verifier-based reranking. Existing TTC scaling strategies and reasoning scorers remain fragmented, evaluated under inconsistent protocols, and are rarely analyzed through the lens of quality-cost trade-offs. We introduce ThinkBooster, a unified framework for seamless test-time compute scaling of LLM reasoning, which consists of (i) a modular Python library implementing state-of-the-art TTC scaling strategy and scorer families, (ii) a benchmark that jointly evaluates performance and compute efficiency, and (iii) a deployable OpenAI-compatible proxy service that enables drop-in integration of adaptive reasoning into real-world applications. We further provide a demo visual debugger for inspecting the reasoning trajectories and escalation decisions. Empirical results on mathematical and coding tasks reveal the performance-compute trade-offs of TTC scaling strategies and scoring methods, and demonstrate that ThinkBooster provides practical gains in real-world tasks. The code is available online under an MIT license.

ACL 2026

G-D7 ThinkBooster: A Unified Framework for Seamless Test-Time Scaling of LLM Reasoning

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. <br>
[Full Message from General Chair Philipp Koehn](https://drive.google.com/file/d/1QiJFOmMjvDgsDo3i1XzlQnImxe3RU_Cy/view?usp=sharing) <br><br><br>
<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>
<br><br><br><br>

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

demo

We present TartanMaroon, a deployable multi-agent academic advising system that handles the full complexity spectrum of student queries, from factual lookups to constrained multi-semester planning. 
We make three contributions: (1) a proposal--critique negotiation protocol in which a Planning Agent generates degree plans evaluated in parallel by domain-specialized agents, enabling detection of cross-domain constraint violations that single-pass outputs miss; (2) a real-time transparency interface streaming agent reasoning and 
negotiation rounds to users, validated by pilot feedback showing increased trust over standard LLM chatbots; and (3) TartanBench, a difficulty-stratified benchmark of 220 advising queries across five complexity tiers, released open-source without exposing individual student records. A five-configuration ablation study establishes a complexity–necessity: single-agent systems perform competitively on simple queries, while multi-agent coordination yields gains of up to $+31$ points on planning tasks.

G-D8 TartanMaroon: Multi-Agent Academic Advising with Iterative Negotiation and Transparent Collaboration

In the era of big data, access to abundant data is crucial to driving research forward. However, such data are often inaccessible due to privacy concerns or high costs, particularly in the healthcare domain. Generating synthetic (tabular) data can address this, but existing models typically require substantial amounts of data to train effectively, contradicting our objective of solving data scarcity. To address this challenge, we propose a novel framework to generate synthetic tabular data, powered by large language models (LLMs) that emulates the architecture of a Generative Adversarial Network (GAN). By incorporating the data generation process as contextual information and utilizing LLM as the optimizer, our approach significantly enhances the quality of synthetic data generation in common scenarios with small sample sizes. Our experimental results on public and private datasets demonstrate that our model outperforms several state-of-art models regarding generating higher quality synthetic data for downstream tasks while keeping the privacy of the real data in low data regime. Code is available at https://github.com/yling1105/MALLM-GAN.

MALLM-GAN: Multi-Agent Large Language Model as Generative Adversarial Network for Synthesizing Tabular Data

Large language models (LLMs) have emerged as a powerful tool for synthetic data generation. A particularly important use case is producing synthetic replicas of private text, which requires carefully balancing privacy and utility. We propose Realistic and Privacy-Preserving Synthetic Data Generation (RPSG), which uses private seeds and integrates privacy-preserving strategies, including a formal differential privacy (DP) mechanism in the candidate selection, to generate realistic synthetic data. Comprehensive experiments against state-of-the-art private synthetic data generation methods demonstrate that RPSG achieves high fidelity to private data while providing strong privacy protection.

Private Seeds, Public LLMs: Realistic and Privacy-Preserving Synthetic Data Generation

Designing effective task-level prompts is crucial for improving the performance of Large Language Models (LLMs). While prior work on instruction induction demonstrates that LLMs can infer better instructions with limited examples, existing approaches often rely on input-output pairs, where obtaining labeled answers can be difficult or costly. To address this limitation, we propose Strategy-Induct, a framework that derives task-level instructions solely from a small set of example questions without requiring labeled answers. Our approach first prompts the model to generate explicit reasoning strategies for each question, forming (strategy, question) pairs. These pairs are then used to induce a task instruction that guides reasoning. Experiments across multiple tasks and model scales demonstrate that Strategy-Induct outperforms state-of-the-art methods in question-only settings. Furthermore, we observe that jointly utilizing LLMs and Large Reasoning Models for both task instruction generation and inference can lead to further performance improvements.

Strategy-Induct: Task-Level Strategy Induction for Instruction Generation

Large Language Models (LLMs) are widely used to generate plausible text on online platforms, without revealing the generation process.
As users increasingly encounter such black-box outputs, detecting hallucinations has become a critical challenge.
To address this challenge, we focus on developing a hallucination detection framework for black-box generators.
Motivated by the observation that hallucinations, once introduced, tend to persist, we sample future contexts.
The sampled future contexts provide valuable clues for hallucination detection and can be effectively integrated with various sampling-based methods.
We extensively demonstrate performance improvements across multiple methods using our proposed sampling approach.

Enhancing Hallucination Detection via Future Context

We perform in-depth evaluations of in-context learning (ICL) on state-of-the-art transformer, state-space, and hybrid large language models over two categories of knowledge-based ICL tasks. Using a combination of behavioral probing and intervention-based methods, we have discovered that, while LLMs of different architectures can behave similarly in task performance, their internals could remain different. We discover that function vectors (FVs) responsible for ICL are primarily located in the self-attention and Mamba layers, and speculate that Mamba2 uses a different mechanism from FVs to perform ICL. FVs are more important for ICL involving parametric knowledge retrieval, but not for contextual knowledge understanding. Our work contributes to a more nuanced understanding across architectures and task types. Methodologically, our approach also highlights the importance of combining both behavioural and mechanistic analyses to investigate LLM capabilities.

Understanding In-Context Learning Beyond Transformers: An Investigation of State Space and Hybrid Architectures

Do reasoning models have "Aha!" moments?
Prior work suggests that models like DeepSeek-R1-Zero undergo sudden mid-trace realizations that lead to accurate outputs, implying an intrinsic capacity for self-correction. 
Yet, it remains unclear whether such intrinsic shifts in reasoning strategy actually improve performance.
Here, we study mid-reasoning shifts and instrument training runs to detect them. 
Our analysis spans $1$M+ reasoning traces, hundreds of training checkpoints, three reasoning domains, and multiple decoding temperatures and model architectures.
We find that reasoning shifts are rare, do not become more frequent with training, and seldom improve accuracy, indicating that they do not correspond to prior perceptions of model insight. 
However, their effect varies with model uncertainty. Building on this finding, we show that artificially triggering extrinsic shifts under high entropy reliably improves accuracy. 
Our results show that mid-reasoning shifts are symptoms of unstable inference behavior rather than an intrinsic mechanism for self-correction.

The Illusion of Insight in Reasoning Models

Large language models (LLMs) seem to offer an easy path to interpretability: just ask them to explain their answers. Yet the features driving an answer often differ from those emphasized in its explanation, meaning post-hoc rationales can misrepresent what actually shaped the model's output. We quantify this gap by comparing the feature-importance distributions of answers and their explanations. Prior analyses reveal such discrepancies, but large-scale study has been limited by the high computational cost of attribution methods. To address this, we introduce the Post-hoc Self-Consistency Bank (PSCB), a large-scale benchmark linking model decisions with diverse explanations and attribution vectors across datasets, methods, and model families. Using PSCB, we find that Spearman rank correlation provides a more reliable signal of alignment than cosine similarity. Building on this insight, we apply Direct Preference Optimization (DPO) to attribution-based preference data, improving alignment without degrading task accuracy, and show that standard supervised fine-tuning on the same data fails to achieve comparable gains. These improvements generalize robustly across domains, paving the way toward scalable and faithful alignment between LLM decisions and their natural language explanations.

Aligning What LLMs Do and Say: Towards Self-Consistent Explanations

Agentic Reinforcement Learning (Agentic RL) has achieved notable success in enabling agents to perform complex reasoning and tool use. However, most methods still relies on sparse outcome-based reward for training. Such feedback fails to differentiate intermediate reasoning quality, leading to suboptimal training results. In this paper, we introduce \textbf{Agent Reasoning Reward Model (Agent-RRM)}, a multi-faceted reward model that produces structured feedback for agentic trajectories, including (1) an explicit reasoning trace , (2) a focused critique that provides refinement guidance by highlighting reasoning flaws, and (3) an overall score that evaluates process performance. Leveraging these signals, we systematically investigate three integration strategies: \textbf{Reagent-C} (text-augmented refinement), \textbf{Reagent-R} (reward-augmented guidance), and \textbf{Reagent-U} (unified feedback integration). Extensive evaluations across 12 diverse benchmarks demonstrate that Reagent-U yields substantial performance leaps, achieving 43.7% on GAIA and 46.2% on WebWalkerQA, validating the effectiveness of our reasoning reward model and training schemes. Code, models, and datasets will be released to facilitate future research.

 Exploring Reasoning Reward Model for Agents

Code localization is a primary bottleneck in automated software development. While parallel tool execution can accelerate discovery, existing agents suffer from a 34.9% redundant tool invocation rate, negating the benefits of parallelism. We introduce FuseSearch, which reframes parallel code localization as a quality--efficiency co-optimization problem. By defining tool efficiency---the ratio of novel information gain to total invocations---we employ a two-stage SFT and RL pipeline to train models in adaptive parallel strategies. Unlike fixed-breadth methods, FuseSearch dynamically adjusts search breadth based on task context, transitioning from exploration to refinement. On SWE-bench Verified, FuseSearch-4B matches SOTA performance (84.7% file-level and 56.4% function-level 
$F_1$ scores) while being 93.6% faster, using 67.7% fewer turns and 68.9% fewer tokens. Our findings demonstrate that efficiency-aware training inherently boosts quality by eliminating noisy, redundant signals, enabling high-performance, low-cost localization agents. Code: \url{https://github.com/sxthunder/FuseSearch}

Downloads

Next from ACL 2026

G-D8 TartanMaroon: Multi-Agent Academic Advising with Iterative Negotiation and Transparent Collaboration

Similar lecture

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