Papers with token consumption
BrowseConf: Confidence-Guided Test-Time Scaling for Web Agents (2026.findings-acl)
Copied to clipboard
Litu Ou, Kuan Li, Huifeng Yin, Liwen Zhang, Zhongwang Zhang, Xixi Wu, Rui Ye, Zile Qiao, Yong Jiang, Pengjun Xie, Fei Huang, Jingren Zhou
| Challenge: | Existing work on confidence in LLMs is limited. |
| Approach: | They propose to use confidence scores to determine model answer quality and encourage model to try again until it reaches satisfactory confidence level. |
| Outcome: | The proposed methods significantly reduce token consumption while demonstrating competitive performance compared to baseline fixed budget methods. |
VortexPIA: Indirect Prompt Injection Attack against LLMs for Efficient Extraction of User Privacy (2026.findings-eacl)
Copied to clipboard
| Challenge: | Large language models (LLMs) have been widely deployed in Conversational AIs . however, the methods proposed in the study rely on a white-box setting . |
| Approach: | They propose an indirect prompt injection attack that induces privacy extraction in LLMs . they use token-efficient data containing false memories to inject LLM data . |
| Outcome: | The proposed method outperforms baselines and achieves state-of-the-art performance. |
Test-Time Strategies for More Efficient and Accurate Agentic RAG (2026.acl-srw)
Copied to clipboard
Abhinav Sharma, Brian Zhang, Deepti Guntur, Zhiyang Zuo, Shreyas Chaudhari, Wenlong Zhao, Franck Dernoncourt, Puneet Mathur, Ryan A. Rossi, Nedim Lipka
| Challenge: | Retrieval-Augmented Generation (RAG) systems face challenges with complex, multi-hop questions. |
| Approach: | They propose to integrate contextualization module and de-duplication module to improve the accuracy of retrieved documents and to reduce the number of turns by 10.5%. |
| Outcome: | The proposed approach achieves a 5.6% increase in EM score and reduces the average number of turns by 10.5% compared to the baseline. |
EASYTOOL: Enhancing LLM-based Agents with Concise Tool Instruction (2025.naacl-long)
Copied to clipboard
| Challenge: | EASYTOOL combines tools from diverse tool documentation into a single tool instruction. |
| Approach: | They propose a framework that transforms tool documentation into a unified tool instruction. |
| Outcome: | EASYTOOL combines extensive tool documentation into a concise tool instruction . it reduces token consumption and improves performance of LLM-based agents . |
Lil: Less is Less When Applying Post-Training Sparse-Attention Algorithms in Long-Decode Stage (2026.findings-acl)
Copied to clipboard
Junhao Hu, Fangze Li, Mingtao Xu, Feifan Meng, Shiju Zhao, Tiancheng Hu, Ting Peng, Anmin Liu, Wenrui Huang, Chenxu Liu, Ziyue Hua, Tao Xie
| Challenge: | Prior work typically decomposes inference into prefill and decode stages, with the decode stage dominating total latency. |
| Approach: | They propose an algorithm that detects threshold where information loss exceeds information gain during sparse decoding to reduce token consumption by up to 90% and a marginal accuracy degradation of less than 2%. |
| Outcome: | The proposed algorithm reduces token consumption by 90% with a marginal accuracy degradation of less than 2% across reasoning-intensive benchmarks. |
EquivPruner: Boosting Efficiency and Quality in LLM-Based Search via Action Pruning (2026.acl-long)
Copied to clipboard
| Challenge: | Existing semantic similarity methods struggle to accurately identify semantically equivalent steps in domain-specific contexts like mathematical reasoning. |
| Approach: | They propose a simple yet effective approach that identifies and prunes semantically equivalent actions during LLM reasoning search. |
| Outcome: | The proposed approach reduces token consumption while improving reasoning efficiency and accuracy on Qwen2.5-Math-7B-Instruct on GSM8K. |
AMA: Adaptive Memory via Multi-Agent Collaboration (2026.findings-acl)
Copied to clipboard
Weiquan Huang, Zixuan Wang, Hehai Lin, Sudong Wang, Bo Xu, Qian Li, Beier Zhu, Linyi Yang, Chengwei Qin
| Challenge: | Existing approaches to longterm memory rely on rigid retrieval granularity, accumulation-heavy maintenance strategies, and coarse-grained update mechanisms. |
| Approach: | They propose a framework that leverages coordinated agents to manage memory across multiple granularities. |
| Outcome: | The proposed framework outperforms state-of-the-art benchmarks while reducing token consumption by approximately 80%. |
ACR: Adaptive Context Refactoring via Context Refactoring Operators for Multi-Turn Dialogue (2026.findings-acl)
Copied to clipboard
Jiawei Shen, Jia Zhu, Hanghui Guo, Weijie Shi, Yue Cui, Qingyu Niu, Guoqing Ma, Jingjiang Liu, Yidan Liang, Yilin Wang, Shimin Di, Jiajie Xu
| Challenge: | Existing approaches to multi-turn dialogues lack contextual consistency and dependencies, and models struggle to maintain factual faithfulness as interaction turns increase. |
| Approach: | They propose an adaptive context refactoring framework that monitors and reshapes the interaction history to mitigate contextual inertia and state drift. |
| Outcome: | The proposed model outperforms baselines while reducing token consumption. |
TopoDIM: One-shot Topology Generation of Diverse Interaction Modes for Multi-Agent Systems (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing communication topologies rely on spatio-temporal dialogues, which incur high latency and computation. |
| Approach: | They propose a framework for one-shot Topology generation with Diverse Interaction Modes that enables agents to construct heterogeneous communication without iterative coordination. |
| Outcome: | The proposed framework reduces total token consumption by 46.41% while improving average performance by 1.50% over state-of-the-art methods. |
AgentOCR: Reimagining Agent History via Optical Self-Compression (2026.acl-long)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have enabled agentic systems trained with reinforcement learning over multi-turn interaction, but practical deployment is bottlenecked by rapidly growing textual histories that inflate token and memory costs. |
| Approach: | They propose a framework that represents the accumulated observation-action history as a compact rendered image. |
| Outcome: | The proposed framework preserves over 95% of text-based agent performance while significantly reducing token consumption (>50%), yielding consistent token and memory efficiency. |
EMA: An Episodic Memory Agent for Efficient and Selective Memory (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing memory-augmented methods often incorporate full dialog histories without filtering, resulting in information redundancy and inference latency. |
| Approach: | They propose a framework that abstracts conversational context into Episodic Memory Units (EMUs) they propose EMA, MemDecider and a filtering decision module to reduce noise and improve overall performance. |
| Outcome: | The proposed framework reduces token consumption by 11.48% while improving performance on two widely-used benchmarks. |
EcoLANG: Efficient and Effective Agent Communication Language Induction for Social Simulation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models (LLMs) have demonstrated impressive ability to role-play humans and replicate complex social dynamics. |
| Approach: | They propose an efficient agent communication language induction for social simulations that reduces token consumption by over 20%. |
| Outcome: | The proposed model reduces token consumption by over 20% while preserving human language. |
VizoMem: A Visual-Textual Memory Framework for Efficient Long-Horizon Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing systems that use long-context modeling incur computational and memory overhead. |
| Approach: | They propose a visual memory framework that pre-rendered text into structured images and stored as visual notes for agentic systems. |
| Outcome: | The proposed system reduces token consumption while preserving effective long-term memory recall. |
Taming "Zombie" Agents: A Markov State-Aware Framework for Resilient Multi-Agent Evolution (2026.acl-long)
Copied to clipboard
Taolin Zhang, Pukun Zhao, Qizhou Chen, Jiuheng Wan, Chen Chen, Xiaofeng He, Chengyu Wang, Richang Hong
| Challenge: | Existing approaches to improve efficiency of multi-agent systems rely on aggressive graph topology evolution . however, such hard pruning overlooks the potential for "zombie" agents to recover and contribute in subsequent discussion rounds. |
| Approach: | They propose a Markov state-aware framework for resilient multi-agent evolution that manages agent collaboration through soft state transitions. |
| Outcome: | The proposed framework outperforms baselines and significantly reduces token consumption through state-aware agent scheduling. |
EcoTune: Token-Efficient Multi-Fidelity Hyperparameter Optimization for Large Language Model Inference (2025.emnlp-main)
Copied to clipboard
| Challenge: | Multi-fidelity optimization improves inference performance with low-fidelity evaluations, but its static scheduling strategies ignore token consumption, leading to high costs. |
| Approach: | They propose a token-efficient multi-fidelity optimization method that optimizes for inference hyperparameters . their method reduces token consumption by over 80% while maintaining or surpassing performance . |
| Outcome: | The proposed method improves over the HELM leaderboard by 7.1%, 24.3%, 21.9%, and 4.6% while maintaining or surpassing performance. |
Can We Afford The Perfect Prompt? Balancing Cost and Accuracy with the Economical Prompting Index (2025.coling-main)
Copied to clipboard
| Challenge: | Prompt engineering is a growing subdiscipline of natural language processing . a lack of appropriate consideration for the financial constraints of computationally burdensome methods can limit their adoption and impact. |
| Approach: | They propose a new metric that combines accuracy scores with token consumption to reflect different resource constraints. |
| Outcome: | The economic prompting index (EPI) measures the performance of 6 prompting techniques across 10 widely-used language models and 4 diverse datasets. |
Chain-of-Memory: Lightweight Memory Construction with Dynamic Evolution for LLM Agents (2026.acl-long)
Copied to clipboard
| Challenge: | Existing paradigms for large language model (LLM) agents use memory construction and retrieval-augmented generation. |
| Approach: | They propose a framework that advocates for a paradigm shift toward lightweight construction paired with sophisticated utilization. |
| Outcome: | Experiments show that CoM outperforms baselines with accuracy gains of 7.5%–10.4% while reducing computational overhead to approximately 2.7% of token consumption and 6.0% of latency compared to complex memory architectures. |
HiSA: Hierarchical State Abstraction for Scalable GUI Agents (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent multimodal large language models (MLLMs) exploit insufficient state abstraction to automate workflows. |
| Approach: | They propose a hierarchical state abstraction approach that actively restructures knowledge rather than passively retaining historical information. |
| Outcome: | The proposed approach achieves a 40.58% success rate while reducing token consumption by 69.85% and monetary costs by 55.10% compared to the best-performing baseline. |
CODESTRUCT: Code Agents over Structured Action Spaces (2026.acl-long)
Copied to clipboard
| Challenge: | LLM-based code agents treat repositories as unstructured text, fail to produce valid patches . authors propose a structure-aware interface that exposes a codebase as a programmable action space . |
| Approach: | They propose to reframe the codebase as a structured action space where agents operate on named AST entities rather than text spans. |
| Outcome: | Evaluated on six LLMs, the proposed framework improves Pass@1 accuracy by 1.2-5.0% and reduces token consumption by 12-38%. |
AgentInit: Initializing LLM-based Multi-Agent Systems via Diversity and Expertise Orchestration for Effective and Efficient Collaboration (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing MAS initialization methods do not fully account for the collaborative needs of the generated agents in subsequent stages. |
| Approach: | They propose to use a Natural Language to Format mechanism to optimize the structure of agent teams and incorporate a natural language to format mechanism to ensure consistency and standardization. |
| Outcome: | The proposed method outperforms state-of-the-art initialization methods and pre-defined strategies across various frameworks and tasks while reducing token consumption. |
Escaping the Sisyphus Dilemma: Experience Replay for Robust Text-to-Optimization Modeling (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing retrieval-augmented strategies for large language models fail to capture dynamic reasoning required to resolve execution failures. |
| Approach: | They propose a framework that implements Experience Replay to transform transient rectification steps into persistent knowledge. |
| Outcome: | The proposed framework improves model accuracy by 8.45% on complex tasks while reducing token consumption by 28.65% and interaction turns by 25.82%. |
LlmLink: Dual LLMs for Dynamic Entity Linking on Long Narratives with Collaborative Memorisation and Prompt Optimisation (2025.coling-main)
Copied to clipboard
| Challenge: | Existing methods focus on supervised fine-tuning or limited to one-off prediction, which poses a challenge where the context is long. |
| Approach: | They propose a dynamic approach to CoREFerence resolution in chunked long narratives by deploying dual Large Language Models. |
| Outcome: | The proposed model achieves performance gains over existing models and fine-tuning approaches on long narrative datasets, significantly reducing the resources required for inference and training. |
Investigating Inference-time Scaling for Chain of Multi-modal Thought: A Preliminary Study (2025.findings-acl)
Copied to clipboard
| Challenge: | Inference-time scaling of chain-of-thought (CoT) has been demonstrated as a promising approach for addressing multi-modal reasoning tasks. |
| Approach: | They propose to integrate visual and textual modalities within the reasoning process . they adopt a consistency-enhanced verifier to ensure effective guidance for both methods across different thought paradigms. |
| Outcome: | The proposed method outperforms text-only reasoning on 10 tasks spanning diverse domains and requires higher token consumption for processing richer visual inputs. |
Resource-Friendly Dynamic Enhancement Chain for Multi-Hop Question Answering (2025.findings-acl)
Copied to clipboard
Binquan Ji, Haibo Luo, YifeiLu YifeiLu, Lei Hei, Jiaqi Wang, Tingjing Liao, Wang Lingyu, Shichao Wang, Feiliang Ren
| Challenge: | Existing approaches to solve multi-hop question answering challenges require multiple rounds of retrieval and iterative generation. |
| Approach: | They propose a framework that decomposes complex questions into coherent subquestions . it then iteratively refines these subquests through context-aware rewriting to generate effective query formulations. |
| Outcome: | The proposed framework performs on par with or surpasses state-of-the-art benchmarks while significantly reducing token consumption. |
Step-GRPO: Internalizing Dynamic Early Exit for Efficient Reasoning (2026.acl-long)
Copied to clipboard
| Challenge: | Large reasoning models that use long chain-of-thought excel at problem-solving but waste computational resources. |
| Approach: | They propose a framework that internalizes dynamic early-exit capabilities directly into the model. |
| Outcome: | The proposed framework reduces token consumption by 32.0% on a Qwen3-8B model compared to the vanilla model . |
HIPO: A Hierarchical Prompt Optimization Framework with Task Awareness and Fine-Grained Debugging (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for prompt optimization apply the same prompt across all samples . existing methods ignore variation in sample difficulty . |
| Approach: | They propose a framework that shifts the paradigm from dataset-level to sample-level optimization. |
| Outcome: | The proposed framework outperforms baselines on 27 tasks and reduces API calls, token consumption and overall cost by 1.2 to 80. |
NeuReasoner: Towards Explainable, Controllable, and Unified Reasoning via Mixture-of-Neurons (2026.acl-long)
Copied to clipboard
| Challenge: | Existing Large Reasoning Models (LRMs) lack explainability and controllability . Existing models target isolated levels without unification, while relying on RL . |
| Approach: | They propose an explainable, controllable, and unified reasoning framework driven by MoN. |
| Outcome: | The proposed framework achieves performance gains of 27.0% while reducing token consumption by 19.6% 63.3%. |
Enhancing Mathematical Reasoning in LLMs by Stepwise Correction (2025.acl-long)
Copied to clipboard
| Challenge: | Existing Best-of-N decoding methods often lead to incorrect solutions . a novel method is proposed to help large language models identify and revise incorrect steps in their generated reasoning paths. |
| Approach: | They propose a method that helps large language models identify and revise incorrect steps in their generated reasoning paths. |
| Outcome: | The proposed method outperforms the state-of-the-art Best-ofN decoding method by +2.4 and reduces token consumption by 77.8%. |
FoE: Forest of Errors Makes the First Solution the Best in Large Reasoning Models (2026.acl-long)
Copied to clipboard
| Challenge: | Recent Large Reasoning Models (LRMs) have demonstrated remarkable success in complex reasoning tasks. |
| Approach: | They propose a self-guided efficient reasoning framework that reduces FoE by pruning subs. |
| Outcome: | The proposed model outperforms eight competitive baselines while reducing token consumption by 37.7% 70.4%. |
Collision to Cognition: Hash-Driven Graph Construction for Efficient RAG (2026.acl-long)
Copied to clipboard
Chuang Zhou, Zheng Yuan, Linhao Luo, Zhaozhuo Xu, Yilin Xiao, Junnan Dong, Siyu An, di Yin, Xing Sun, Xiao Huang
| Challenge: | Retrieval-augmented generation (RAG) has been used for enhancing large language models with external knowledge. |
| Approach: | They propose a framework for mining efficient graph structures via hashing to enhance RAG . they adopt an inductive paradigm where global graph structure emerges from local hash collisions . |
| Outcome: | The proposed framework outperforms existing baselines while requiring no GPU resources or token budget. |
MemPO: Self-Memory Policy Optimization for Long-Horizon Agents (2026.findings-acl)
Copied to clipboard
Ruoran Li, Xinghua Zhang, Haiyang Yu, Shitong Duan, Xiang Li, Wenxin Xiang, Chonghua Liao, Xudong Guo, Yongbin Li, Jinli Suo
| Challenge: | Existing methods for long-horizon agents introduce the external memory module and look up the relevant information from the stored memory, which prevents the model from proactively managing its memory content and aligning with the agent’s overarching task objectives. |
| Approach: | They propose an algorithm which enables agents to autonomously manage their memory during interaction with environment and selectively retain crucial information. |
| Outcome: | Extensive experiments show that the proposed algorithm achieves absolute F1 score gains of 25.98 over the base model and 7.1 over the previous SOTA baseline while preserving task performance. |
EvoHyper: Evolving Hypergraph Topologies for Unified Collaboration in Multi-Agent Communication (2026.findings-acl)
Copied to clipboard
Heng Zhang, Yihao Zhong, Lubin Gan, Zhihe Chen, Jiajun Wu, Yuling Shi, Xiaodong Gu, Hao Zhang, Haochen You, Jin Huang
| Challenge: | Existing methods for multi-agent collaboration use a fixed communication graph and manage collaboration structure and shared memory in separate modules. |
| Approach: | They propose a framework that uses an evolving hypergraph topology for multi-agent collaboration. |
| Outcome: | The proposed framework achieves 3.2% to 7.8% accuracy gains over state-of-the-art methods and efficient, reducing token consumption by up to 23.5%. |
Divide-Then-Aggregate: An Efficient Tool Learning Method via Parallel Tool Invocation (2025.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) demonstrate remarkable capabilities but their ability to autonomously execute complex real-world tasks remains limited. |
| Approach: | They propose a parallel tool invocation framework that decomposes tasks into parallel tool-using subtasks while aggregating results for subsequent decisions. |
| Outcome: | The proposed method significantly improves task performance while reducing token consumption and inference time. |
NeuralFSM: Adaptive Multi-Agent Coordination via Learning Finite-State Execution Policy (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to multi-agent problem solving rely on hand-crafted protocols or automatically designed topologies. |
| Approach: | They propose a state-driven framework that formulates multi-agent problem solving as a finite-state execution process. |
| Outcome: | The proposed framework outperforms baselines on diverse benchmarks by 6.74%–19.39% while reducing token consumption. |
Q2EI: Query-to-Entity Inference for Semantic Condensation in Domain-Specific Retrieval (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing generative expansions introduce redundancy or hallucinations that cause semantic drift. |
| Approach: | They propose a query rewriting strategy that reframes rewrite as semantic condensation rather than expansion. |
| Outcome: | The proposed method outperforms baselines on medical and legal benchmarks while reducing token consumption. |
Valid Necessary: Diagnosing Latent Inefficiency in Chain-of-Thought (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing reasoning step evaluators fail to distinguish “valid but inefficient” reasoning steps from necessary reasoning. |
| Approach: | They propose a training-free metric that identifies low-utility steps and a post-hoc compression strategy to quantify their impact on token usage. |
| Outcome: | The proposed metric reduces token consumption by 31–53% while maintaining accuracy at substantially higher compression rates. |
Nash-Pruned CredMAS: Dynamic Panel Pruning for VLM-MAS using Nash-based Selection and Doubly-Robust Credits (2026.findings-acl)
Copied to clipboard
| Challenge: | Multi-Agent Systems (MAS) are expensive due to static panel designs, where all N agents communicate at every T round. |
| Approach: | They propose an economic framework that transforms agent selection into a dynamic resource allocation game. |
| Outcome: | The proposed system reduces token consumption by over 25% on challenging benchmarks while reducing token consumption. |
BioProAgent: Neuro-Symbolic Grounding for Constrained Scientific Planning (2026.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) have demonstrated significant reasoning capabilities in scientific discovery but struggle to bridge the gap to physical execution in wet-labs. |
| Approach: | They propose a framework that anchors probabilistic planning in a deterministic Finite State Machine (FSM) they propose reducing token consumption by 6 through symbolic abstraction to address context bottlenecks . |
| Outcome: | The proposed framework achieves 95.6% physical compliance, compared to 21.0% for ReAct, in the extended BioProBench benchmark. |
Seer Self-Consistency: Advance Budget Estimation for Adaptive Test-Time Scaling (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated exceptional performance in reasoning tasks, particularly in mathematics. |
| Approach: | They propose a dynamic self-consistency framework that integrates System 1 and System 2 reasoning to improve token efficiency and latency. |
| Outcome: | The proposed method outperforms existing methods, achieving up to 47% reduction in token consumption and 43% reduction in inference latency without significant performance loss. |
EconProver: Towards More Economical Test-Time Scaling for Automated Theorem Proving (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have recently advanced the field of Automated Theorem Proving (ATP) Existing cost analyses regulate only the number of sampling passes, ignoring the substantial disparities in sampling costs. |
| Approach: | They propose to integrate two complementary methods into a unified EconRL pipeline to increase pass rates under constrained sampling passes. |
| Outcome: | The proposed method reduces token usage and sample passes while maintaining the original performance. |
NaturalGAIA: A Verifiable Benchmark and Hierarchical Framework for Long-Horizon GUI Tasks (2026.acl-long)
Copied to clipboard
| Challenge: | Current research faces an "Evaluation-Realism Dilemma" due to unstable MLLM judges or manual verification. |
| Approach: | They propose a verifiable evaluation dataset grounded in real-world human GUI intents. |
| Outcome: | The proposed framework outperforms the state-of-the-art framework in achieving a weighted pathway success rate of 45.6% while reducing token consumption and execution time by 76%. |