United States

Large language models (LLMs) face a fundamental trade-off between factual consistency and reasoning diversity. Deterministic decoding strategies prioritize reliability but may fail to explore alternative solution paths, while high-temperature sampling increases exploration at the cost of factual accuracy. We present FROST (Factual Reasoning via Optimized Stochastic Trajectories), an inference framework that systematically balances exploration and exploitation for cost-efficient reasoning in production environments. FROST combines deterministic inference from large models with targeted stochastic sampling from smaller models, followed by multi-criteria validation to select factually grounded outputs. The framework operates entirely at inference time, requiring no additional training or fine-tuning. Across HotpotQA, CommonsenseQA, and MMLU, FROST achieves 3--5\% accuracy improvements over standard chain-of-thought prompting. Crucially, it maintains high cost-efficiency relative to other robust inference methods, achieving a 28\% cost reduction compared to Self-Consistency ensembles through strategic delegation to smaller models. Validation analysis demonstrates that FROST reduces unsupported outputs by 40\% relative to baseline methods. Task-stratified evaluation reveals that exploration benefits scale with problem ambiguity, with alternative reasoning paths improving accuracy in 23--34\% of multi-hop questions. These results establish FROST as a practical approach for deploying reliable and efficient reasoning systems in production environments.

ACL 2026

FROST: Factual Reasoning via Optimized Stochastic Trajectories in Large Language Models during Inference

## 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.

poster

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.

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.

Extracting structured data from unstructured text using large language models (LLMs) becomes challenging when the target schemas are large and complex. In such cases, including the full schema in the prompt increases cost and latency, risks lost-in-the-middle performance degradation, and can exceed context length limits. We propose SchemaRAG, a retrieval-augmented generation (RAG) framework that dynamically prunes the output schema space for schema-conditioned information extraction tasks by leveraging schema metadata and few-shot examples (when available). We evaluate SchemaRAG on real-world healthcare and e-commerce datasets. Our results show that SchemaRAG can achieve up to an 8.8% increase in micro-F1, a 47% reduction in latency, and a 48% reduction in token costs, demonstrating its practicality for large-schema extraction.

SchemaRAG: Dynamic Large Schema Reduction for LLM-driven Structured Information Extraction

Enterprise IT support interactions are fundamentally diagnostic: effective resolution requires iterative evidence gathering from ambiguous user reports to identify an underlying root cause. While retrieval-augmented generation (RAG) provides grounding through historical cases, standard multi-turn RAG systems lack explicit diagnostic state and therefore struggle to accumulate evidence and resolve competing hypotheses across turns.


We introduce DQA, a diagnostic question-answering framework that maintains persistent diagnostic state and aggregates retrieved cases at the level of root causes rather than individual documents. DQA combines conversational query rewriting, retrieval aggregation, and state-conditioned response generation to support systematic troubleshooting under enterprise latency and context constraints.


We evaluate DQA on 150 anonymized enterprise IT support scenarios using a replay-based protocol. Averaged over three independent runs, DQA achieves a 78.7\% success rate under a trajectory-level success criterion, compared to 41.3\% for a multi-turn RAG baseline, while reducing average turns from 8.4 to 3.9. This improvement reflects the benefit of explicitly representing competing explanations and aggregating evidence across turns in unscripted troubleshooting.

DQA: Diagnostic Question Answering for IT Support

We introduce Agentic Economic Modeling (AEM), a framework that aligns synthetic LLM choices with small-sample human evidence for reliable econometric inference. AEM first generates task-conditioned synthetic choices via LLMs, then learns a bias-correction mapping from task features and raw LLM choices to human-aligned choices, upon which standard econometric estimators perform inference to recover demand elasticities and treatment effects. We validate AEM in two experiments. In a large scale conjoint study with millions of observations, using only 10\% of the original data to fit the correction model lowers the error of the demand-parameter estimates, while uncorrected LLM choices even increase the errors. In a regional field experiment, a mixture model calibrated on 10\% of geographic regions estimates an out-of-domain treatment effect of -65$\pm$10 bps, closely matching the full human experiment (-60$\pm$8 bps). Under time-wise extrapolation, training with only day-one human data yields -24 bps (95\% CI: [-26, -22], p$<$1e-5), improving over the human-only day-one baseline (-17 bps, 95\% CI: [-43, +9], p=0.2049). These results demonstrate AEM's potential to improve RCT efficiency and establish a foundation method for LLM-based counterfactual generation.

Agentic Economic Modeling

Reinforcement learning (RL) has become a cornerstone of the post-training pipeline for large language models (LLMs), enabling capabilities such as complex reasoning and tool use. However, standard RL approaches face significant challenges due to reward sparsity. Moreover, LLMs typically exhibit mode-seeking behavior, concentrating probability mass on high-likelihood regions. This lack of diversity biases the model toward premature exploitation, hindering the exploration necessary for optimal learning. To address this, we propose VEG (verbal $\epsilon$-greedy), a novel framework that leverages external feedback as a dynamic control variable to explicitly balance exploration and exploitation within the semantic space. This method not only supplements sparse final rewards with intermediate signals but also enforces sustained exploration throughout the training process. Experiments on Tau Bench and SearchQA demonstrate that our method achieves superior accuracy compared to standard RL baselines. Notably, the trained policy eventually outperforms the external feedback model itself, demonstrating that VEG enables the agent to effectively filter and improve upon the guidance it receives.

VEG: Verbal $\epsilon$-greedy for Semantic Exploration in Multi-Turn RL Agents

Traditional phishing website detection relies on static heuristics or reference lists, which lag behind rapidly evolving attacks. 
While recent systems incorporate large language models (LLMs), they are still prompt-based, deterministic pipelines that underutilize reasoning capability.
We present MemoPhishAgent (MPA), a memory-augmented multi-modal LLM agent that dynamically orchestrates phishing-specific tools and leverages episodic memories of past reasoning trajectories to guide decisions on recurring and novel threats.
On two public datasets, MPA outperforms three state-of-the-art (SOTA) baselines, improving recall by 13.6\%.
To better reflect realistic, user-facing phishing detection performance, we further evaluate MPA on a benchmark of real-world suspicious URLs actively crawled from five social media platforms, where it improves recall by 20\%.
Detailed analysis shows episodic memory contributes up to 27\% recall gain without introducing additional computational overhead.
The ablation study confirms the necessity of the agent-based approach compared to prompt-based baselines and validates the effectiveness of our tool design.
Finally, MPA is deployed in production, processing $\sim60K$ targeted high-risk URLs weekly, and achieving 91.44\% recall, providing proactive protection for millions of customers.
Together, our results show that combining multi-modal reasoning with episodic memory yields robust, adaptable phishing detection in realistic user-exposure settings.

MemoPhishAgent: Memory-Augmented Multi-Modal LLM Agent for Phishing URL Detection

Interactive large language model (LLM) agents operating via multi-turn dialogue and multi-step tool calling are increasingly used in production. Benchmarks for these agents must both reliably compare models and yield on-policy training data. Prior agentic benchmarks (e.g., tau-bench, tau^2-bench, AppWorld) rely on fully deterministic backends, which are costly to build and iterate. We propose Proxy State-Based Evaluation, an LLM-driven simulation framework that preserves final state-based evaluation without a deterministic database. Specifically, a scenario specifies the user goal, user/system facts, expected final state, and expected agent behavior, and an LLM state tracker infers a structured proxy state from the full interaction trace. LLM judges then verify goal completion and detect tool/user hallucinations against scenario constraints. Empirically, our benchmark produces stable, model-differentiating rankings across families and inference-time reasoning efforts, and its on- and off-policy rollouts provide supervision that transfers to unseen scenarios. Careful scenario specification yields near-zero simulator hallucination rates, as supported by ablation studies. The framework also supports sensitivity analyses over user personas. Human-LLM judge agreement exceeds 90%, indicating reliable automated evaluation. Overall, proxy state-based evaluation offers a practical, scalable alternative to deterministic agentic benchmarks for industrial LLM agents.

Toward Scalable Verifiable Reward: Proxy State-Based Evaluation for Multi-turn Tool-Calling LLM Agents

Large language models (LLMs) are increasingly being deployed in cost- and latency-sensitive settings. While chain-of-thought improves reasoning, it can waste tokens on simple requests. We study selective thinking for tool-using LLMs and introduce Adaptive Rejection Sampling (Ada-RS), an algorithm-agnostic sample filtering framework for learning selective and efficient reasoning. For each given context, Ada-RS scores multiple sampled completions with an adaptive length-penalized reward then applies stochastic rejection sampling to retain only high-reward candidates (or preference pairs) for downstream optimization. We demonstrate how Ada-RS plugs into both preference pair (e.g. DPO) or grouped policy optimization strategies (e.g. DAPO). Using Qwen3-8B with LoRA on a synthetic tool call-oriented e-commerce benchmark, Ada-RS improves the accuracy-efficiency frontier over standard algorithms by reducing average output tokens by up to ∼80% and reducing thinking rate by up to ∼95% while maintaining or improving tool call accuracy. These results highlight that training signal selection is a powerful lever for efficient reasoning in latency-sensitive deployments.

Ada-RS: Adaptive Rejection Sampling for Selective Thinking

Multimodal large language models (MLLMs) are effective at capturing the semantics of short video content; however, they often fail to attend to the policy-specific details required for reliable content moderation.
To address this limitation, we introduce IPS, a novel framework that integrates In-prompt Process Supervision into MLLMs by introducing sequential reasoning over ancillary questions during fine-tuning. 
IPS consistently outperforms baseline MLLMs on public and proprietary benchmarks.
Moreover, replacing human-annotated ancillary labels with MLLM-generated ones results in only marginal performance degradation, demonstrating robustness to noisy supervision and strong scalability with model-generated annotations.
These findings establish IPS as a scalable and effective solution for complex multimodal classification in large-scale industrial settings.

IPS: In-Prompt Process Supervision for Short Video Content Moderation

Cascaded LLM systems coordinate models of varying sizes with human experts to balance accuracy, cost, and abstention under uncertainty. However, single-model tiers at each stage falter on ambiguous queries, triggering premature escalations to costlier models or experts due to under-confidence and inefficient compute scaling. **CascadeDebate** addresses this critical gap by inserting multi-agent deliberation directly at each tier's escalation boundary. Confidence-based routers activate lightweight agent ensembles only for uncertain cases, enabling consensus-driven resolution of ambiguities internally, without invoking higher-cost upgrades. Our unified architecture alternates single-model inference with selective multi-agent deliberation across model scales, culminating in human experts as final fallback. This design scales test-time compute dynamically to query difficulty. Across five benchmarks spanning science, medicine, and general knowledge, CascadeDebate outperforms strong single-model cascades and standalone multi-agent systems by up to 26.75%.
An online threshold optimizer proves essential, boosting accuracy 20.98–52.33% relative improvement over fixed policies and enabling elastic adaptation to real-world distributions.

CascadeDebate: Multi-Agent Deliberation for Cost-Aware LLM Cascades

Large Language Model (LLM)-based agents show promise for e-commerce conversational shopping, yet existing implementations lack the interaction depth and contextual breadth required for complex product research. Meanwhile, the Deep Research paradigm, despite advancing information synthesis in web search, suffers from domain gaps when transferred to e-commerce. We propose ProductResearch, a multi-agent framework that synthesizes high-fidelity, long-horizon tool-use trajectories for training robust e-commerce shopping agents. The framework employs a User Agent to infer nuanced shopping intents from behavioral histories, and a Supervisor Agent that orchestrates iterative collaboration with a Research Agent to generate synthetic trajectories culminating in comprehensive, insightful product research reports. These trajectories are rigorously filtered and distilled through a reflective internalization process that consolidates multi-agent supervisory interactions into coherent single-role training examples, enabling effective fine-tuning of LLM agents for complex shopping inquiries. Extensive experiments show that a compact MoE model fine-tuned on our synthetic data achieves substantial improvements over its base model in response comprehensiveness, research depth, and user-perceived utility, approaching the performance of frontier proprietary deep research systems and establishing multi-agent synthetic trajectory training as an effective and scalable paradigm for enhancing LLM-based shopping assistance.

Downloads

Next from ACL 2026

SchemaRAG: Dynamic Large Schema Reduction for LLM-driven Structured Information Extraction

Similar lecture

Answer Convergence as a Signal for Early Stopping in Reasoning