Large Language Models

Follow this field Ask about this field

Recent momentum

emerging

0 papers in the last 28 days · 0.0% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this field, kept on the site without email delivery.

Period ending 2026-09-21

21 new papers

A weekly snapshot of new work published in Large Language Models.

Period ending 2026-09-14

22 new papers

A weekly snapshot of new work published in Large Language Models.

Period ending 2026-09-07

36 new papers

A weekly snapshot of new work published in Large Language Models.

Inside this field

Focused directions

Focused topic

Large Language

Within Large Language Models

417 papersExplore

Focused topic

Large Language Model Performance

Within Large Language Models

260 papersExplore

Focused topic

Large Language Models(Llms

Within Large Language Models

85 papersExplore

Focused topic

Large Language Model Output

Within Large Language Models

60 papersExplore

Focused topic

Large Language Model Calls

Within Large Language Models

49 papersExplore

847 papers

Latest in Large Language Models

Browse all topics →

COMED: The Missing Middle Between Routing and Collaboration in Multi-LLM Inference
Sep 22, 2026Norah Alballa, Wenxuan Zhang, Salma Kharrat +4Large Language Model Performance
Semantic Abstraction for Natural Language Inference: a Methodological Framework for Discovering and Compensating Semantic Knowledge and Reasoning Gaps in Large Language Models
Sep 22, 2026David Torres-Moreno, Jorge Hermosillo-ValadezNatural Language Inference Semantic Gap
Constrained Decoding Eliminates Structural Failures in Small LLMs but Reveals a Scale-Dependent Semantic Gap
Sep 20, 2026Akash ChavanLarge Language Model Performance
Edustories: A Collection of Real-world Case Studies from Classroom Practices
Sep 17, 2026Michal Štefánik, Jan Nehyba, Jirina Karasova +4Classrooms Case Study
Before the Arrest: Benchmarking LLMs on Criminal Profiling from Incomplete Evidence
Sep 17, 2026Yutong Yao, Yanjie Cao, Guanhua Chen +5Crime Domain Profiling
Semantic Layer Induction from Raw Telemetry via Hierarchical LLM and RAG Abstraction
Sep 17, 2026Yuanzhe Jia, Ali AnaissiMultivariate Telemetry Data Data Lakes
Playing log(N)-Questions over Wikipedia Abstracts: How Per-Round Errors Compound Under Information Asymmetry
Sep 16, 2026Peter PotashFrontier Models Large Language Model Performance
GYROval: A Robust Benchmark for Cultural Value Orientation in Large Language Models
Sep 16, 2026Alexander Didenko, Anna Shabanova, Vladislav Zapylikhin +2Cultural Knowledge Large Language
BENCHCOMPASS: From Scores to Signals for Training and Harness Decisions in Payment-Domain LLMs
Sep 16, 2026Sijie Dong, Wei Ren, Xuanwei Hu +9Knowledge-Grounded Reasoning Large Language
PentestChain: A Cost-Aware, MCP-Orchestrated Framework for Automated Penetration Testing with Free-Tier LLMs
Sep 16, 2026Rushabh Vipulkumar Patel, Dipo Dunsin, Mohammed Almaiah +1Penetration Testing Exploitation
An Empirical Evaluation of Cost-Efficient Large Language Models on Algorithmic Programming Tasks
Sep 16, 2026Chandimal Adikari, Nandika HerathCode Generation Large Language
A Four-Stage Decomposition of Word-Problem Solving and Mechanistic Fragility in LLM Math Reasoning
Sep 15, 2026Zhongdi Qu, Carla P. GomesMath Problems Large Language Model Reasoning
What Breaks Under Pruning in Smart Homes, and When? Evaluating LLM Degradation Across Architectures and Task Complexity
Sep 15, 2026Congjing Zhang, Vashishtha Patil, Henning Lange +1Large Language Model Performance Pruning
Enhancing Accessibility of Medical Texts through Large Language Model-Driven Plain Language Adaptation
Sep 15, 2026Ting-Wei Chang, Hen-Hsen Huang, Hsin-Hsi ChenLarge Language Model Adaptation Large Language
LLMDE: A Large Language Model-Driven Differential Evolution Algorithm for Portfolio Optimization
Sep 15, 2026Rong Chai, Vaclav Snasel, Xiaopeng Wang +2Portfolio Optimization Llm-Based Optimization Modeling
Breaking the 1.58-bit Barrier for Ternary LLMs
Sep 14, 2026Evangelos Georganas, Alexander Heinecke, Pradeep DubeyLarge Language Model Quantization Large Models
Divide, Consult, Conquer: Capability Laundering Through Aligned LLMs
Sep 14, 2026Mark Russinovich, Blake Bullwinkel, Giorgio Severi +2Large Language Model Safety Laundering
The Universe of Universes: Benefit Yield Functions, Implosion Thresholds, and Infrastructure-Aware Optimization in Multi-LLM Systems
Sep 14, 2026Danielle Franklin, Vasu Raj JainLarge Language Multi-Source Retrieval-Augmented Generation
Empirical Evaluation of Open-Source Large Language Models for Retrieval-Augmented Generation in ESG Domain
Sep 14, 2026Motaz Saad, Anna Borrelli, Ivan Gentile +3Large Language Model Performance Large Language
Improving Mathematical Reasoning Capabilities in Large Language Models via Reasoning Process Error Classification
Sep 14, 2026Runa Yoshida, Kosuke Nishida, Kyosuke NishidaMathematical Reasoning Reasoning Errors
Performance, Efficiency and Collapse -- Advantages and Challenges in Offline Post-training of Code LLMs
Sep 14, 2026Abhinav Anand, Sanjana Reddy Pachika, Shweta Verma +1LLM Post-Training Methods Large Language
AIM: A Privacy-Aware Interoperable Memory Framework for Multi-Agent Multi-User LLM Systems
Sep 14, 2026Zachary Johnson, Nigel Boachie Kumankumah, Somya Chatterjee +8Agent Memory Multi-Agent Large Language Model
From Collaboration to Capability: Internalizing Routed LLM Experts into Compact Reasoners
Sep 14, 2026Frank Nie, Shuyao Wang, Ethan B. LiuRecursive Reasoner Experts
Biomedical Reference Generation Remains Unreliable across 26 Large Language Models
Sep 14, 2026Maxim Topaz, Zhihong Zhang, Nir Roguin +3Biomedical Text Large Language
The Stochastic Deputy: Structural Tenant Isolation for Tool-Using LLM Agents
Sep 13, 2026Mirza Samad Ahmed Baig, Syeda Anshrah Gillani, Asher Ali +1Large Language Model Agents Model Context Protocol
RAG-Safety-Bench: Reliable Evaluation of Retrieval-Augmented LLM Safety
Sep 11, 2026Adithiyan Rajan Indira Saravanan, Kathleen C. FraserLarge Language Model Safety Retrieval-Augmented Generation Systems
Phase-Decoupled, Model-Calibrated Power Control for Disaggregated LLM Serving
Sep 11, 2026Jae Gon Kim, Donghoon Yoo, Hanyul Ryu +3Throughput Large Language
But How Would AI Agents Run a Town's Economy?
Sep 11, 2026Sajal Regmi, Siddhartha Pudasaini, Chetan Phakami PunEconomies Multi-Agent Simulations
TransClean: A Benchmark for Detecting and Extracting Clean Translations from Large Language Model Outputs
Sep 11, 2026Shenbin Qian, Yves ScherrerMachine Translation Quality Translation Quality
Building py-kvcache: A Performance Characterization of External KV Caching for vLLM with NVMe SSDs
Sep 11, 2026Joseph Kanichai, Tiziano De Matteis, Animesh TrivediKv-Cache Blocks Key-Value Cache
Negative Self-Distillation: Learning to Reason by Avoiding Flaws
Sep 10, 2026Rongcan Pei, Zhepei Wei, Shuyao Xu +3Unsupervised On-Policy Self-Distillation On-Policy Distillation
LiteRAG: Cost-Efficient Graph-Based Retrieval-Augmented Generation
Sep 9, 2026Daniel Alejandro Coll Tejeda, Pedro García López, Daniel Barcelona-PonsGraph-Based Retrieval Augmented Generation Graph-Based Retrieval
Do Reasoning Representations Help Humans Evaluate LLM Outputs?
Sep 8, 2026Jaewoo Lim, Sungbok Shin, Sanghyun HongLarge Language Model Output Model Interpretability
The Unreliable Progress Bar: Can LLM Agents Reliably Report Task Progress Throughout Execution?
Sep 8, 2026Boyang Wang, Yunhan Wang, Yalun WuLarge Language Model Agents Agent Framework
ACEA: An Adversarial Co-Evolution Arena for Head-to-Head Red-Team and Blue-Team LLM Testing
Sep 8, 2026Yi Ting Shen, Kentaroh Toyoda, Alex LeungLarge Language Model Evaluation Large Language Model Calls
CodeTD: Topology of Attention Detects Hallucinations in Code LLMs
Sep 7, 2026Daria Voronkova, Ilya Trofimov, Anton Dmitriev +3Code Generation Correctness
DCFA: Dual-view Causal-inspired Attribution for Failure Reasoning in LLM-based Multi-agent Systems
Sep 7, 2026Zehao Wang, Lanjun Wang, Shilong Jin +2Multi-Agent Systems Large Language Model Performance
When Financial Fine-tuning Fails: A Three-Level Detectability Analysis of Numerical Hallucination in Domain-Adapted Language Models
Sep 7, 2026Xiaodong Li, Peiwei LiuLarge Language Model Adaptation Hallucinations
Rethinking On-Policy Distillation of Large Language Models II: One Training Example
Sep 3, 2026Zixuan Fu, Bingxiang He, Yuxin Zuo +10On-Policy Distillation Model Training
LLM4CKD: Large Language Models for Early Stage Chronic Kidney Disease Screening
Sep 3, 2026Muhammad Ashad Kabir, Sirajam MuniraChronic Kidney Disease Screening
CROCODIL: Cross-Model Code Editing with LLMs
Sep 3, 2026Linghan Zhong, Aditya Thimmaiah, Jayanth Srinivasa +2Large Language
KhatianDoc: A Human-Verified Benchmark Diagnosing Multimodal LLM Failure on Bengali Legal Land Records
Sep 3, 2026Tasmiad Hasan, Arafat Zaman Ratul, Sarker Sadman Saalim +3Bangla Legal Domain
Lost in Reordering: Structural Sensitivity of Multilingual LLMs under Semantics-Preserving Perturbations
Sep 3, 2026Karthika Nhayakkat, Rajat Verma, Maharaj Brahma +4Multilingual Large Language Models Multilingual Reasoning
GrowPage: On-Demand KV Budgeting for Efficient LLM Reasoning Serving
Sep 3, 2026Qiankun Ma, Yanjiang Zhou, Zinan Xiong +5Graphics Processing Unit Memory Large Language Model Reasoning
It's the Problem, Not the Path: Budget and Difficulty Confounds in LLM Reasoning Trajectories
Sep 3, 2026Yigit Utku BulutLarge Language Model Reasoning Large Language Model Performance
Lngram v2: Latent N-Gram Memory with Interpretable Discrete Representations
Sep 3, 2026Yunao Zheng, Bin Wen, Xiaojie Wang +12N$-Grams Features Graph Language Models
To What Extent Do Large Language Models Understand Bangla Idioms?
Sep 3, 2026Mousumi Akter, Md. Faiyaz Abdullah Sayeedi, Nurul Labib Sayeedi +1Multilingual Idioms Multilingual Large Language Models
From Zero to Hero: An Open LLM Ecosystem for Armenian
Sep 3, 2026Erik Arakelyan, Khatun Avetisyan, Meri Davtyan +5Arabic Natural Language Processing Text Corpora
Large Language Models in Resolving Contextual Knowledge Conflicts
Sep 2, 2026Xinye Yang, Zhenyang Liu, Ruisi Li +1Conflict Large Language Model Performance
Knowing Is Not Enough: Information Retrievability as a Precondition to Effective LLM Oversight
Sep 2, 2026Xinyu Fu, Narayan Ramasubbu, Dennis GallettaLarge Language Model Performance Human Oversight
Thinking effort aligns between humans and reasoning models in abductive reasoning
Sep 1, 2026Henry ArthurLarge Reasoning Models Abductive Reasoning
Citing Less Critically: LLMs Reshape the Rhetoric and Reach of Scientific Citation
Sep 1, 2026Yixuan Liu, Lin Chen, Zhuoqi Liu +2Citations Large Language Model Bias
Ready to Speak: Aligning LLMs for TTS-Friendly Text Generation
Sep 1, 2026Thibaut Thonet, Jos Rozen, Laurent BesacierZero-Shot Text-To-Speech Text Generation
SciTrue: Reliable Scientific Claim Validation with Frontier and Open Language Models at the NTCIR SciClaimEval Task
Sep 1, 2026Qiming Bao, Neşet Özkan Tan, Siyuan Wang +1Noisy Claim Verification Scientific Discovery
Predicting Program Exit Code with LLMs and Programming Language Semantics
Sep 1, 2026Lara Marinov, Aditya Thimmaiah, Jayanth Srinivasa +2Large Language Model Performance
RecalibrateGPT: AI Fatigue Resilient Conversational Interfaces
Sep 1, 2026Nikhil WaniCognitive Load Conversational Artificial Intelligence
QTEA: Ternary LLMs with Sparse Residual Salient Weight and By-Column Optimization
Aug 31, 2026Yipin Guo, Arun M George, Jie Fu +3Weight-Only Quantization Model Weights
Wrong Prediction, Right Answer: Recovering Evidence from Collapsed LLM Sequence Scores
Aug 31, 2026Qiyao Yan, Chenpeng Wang, Liangming PanLarge Language Model Reasoning Reasoning Benchmark
S3C-LLM: Skill-Code Guided Agentic Language Models for Spectrum-to-Structure Elucidation
Aug 31, 2026Xuanle Zhao, Xinyuan Cai, Xiang Cheng +1Spectra Large Language Models(Llms
GMTS: Gradient Magnitude-based Token Selection Improves RLVR Training for LLM Reasoning
Aug 31, 2026Outongyi Lv, Yuanwei Zhang, Xiaoqun ZhangReinforcement Learning With Verifiable Reward Large Language Model Reasoning

Sep 22, 2026 · cs.CLJ/K move · Enter open · S save

COMED: The Missing Middle Between Routing and Collaboration in Multi-LLM Inference

Norah Alballa, Wenxuan Zhang, Salma Kharrat, Fares Fourati+3

No single Large Language Model (LLM) is uniformly reliable across queries, motivating multi-model inference systems that either route among models or combine their outputs. However, routing stops after selecting an initial model, while dense collaboration invokes peers on every query. We show that collaboration is non-monotonic: peers can recover failures that no model solves alone, but can also corrupt initially correct answers. We introduce COMED (Controlled Model Escalation for Multi-LLM Deliberation), a post-anchor controller for selective cross-model collaboration. COMED uses anchor self-consistency, router margin, and a lightweight peer probe to accept confident answers, verify ambiguous cases, and escalate only when collaboration is likely beneficial. We formalize this trade-off with a rescue-harm decomposition showing that selective collaboration improves when rescued errors outweigh collaboration-induced harms. Across medical, scientific, and general reasoning benchmarks, COMED improves fixed and routed anchors in all 16 open-weight settings, with gains up to +10.7 percentage points on MedQA while invoking fewer models and using fewer decoded tokens than dense collaboration. On HLE with frontier models, COMED improves GPT-5.5 from 23.1% to 28.1%, outperforming dense collaboration and achieving the best results.

Large Language Model Performance

Open paper Ask about it PDF