Key papers

• Stale but Stable: Staleness-Adaptive Trust Regions for Stabilizing Asynchronous Reinforcement Learning (2026)
  Junyao Yang et al.
  10.93
• AgentDebugX: An Open-Source Toolkit for Failure Observability, Attribution, and Recovery in LLM Agents (2026)
  Kunlun Zhu et al.
  10.34
• PACE: A Proxy for Agentic Capability Evaluation (2026)
  Yueqi Song et al.
  8.24
• Multi-Agent LLMs Fail to Explore Each Other (2026)
  Hyeong Kyu Choi et al.
  7.36
• Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning (2026)
  Lu Dai et al.
  7.34
• A Controlled Study of Attention-Only Transformers (2026)
  Henry Ndubuaku et al.
  5.96
• Large-Language-Models-as-a-Judge in Theory-Agnostic Adaptive Metric-Alignment for Prototypical Networks in Personality Recognition (2026)
  Jing Jie Tan et al.
  5.89
• Evidence-Backed Video Question Answering (2026)
  Shijie Wang et al.
  5.88
• TUDUM: A Turkish-Thinking Reasoning Pipeline for Qwen3.5-27B (2026)
  Baran Bingol et al.
  5.01
• OpenSafeIntent: Evaluating Intent-Calibrated Safe Completion Across Dual-Use Prompt Sets (2026)
  Rheeya Uppaal et al.
  5.01
• COBART: Controlled, Optimized, Bidirectional and Auto-Regressive Transformer for Ad Headline Generation (2026)
  Yashal Shakti Kanungo et al.
  5.01
• ICDAR 2026 HIPE-OCRepair Competition on LLM-Assisted OCR Post-Correction for Historical Documents (2026)
  Maud Ehrmann et al.
  5.01
• When Synthetic Speech Is All You Have: Better Call GRPO (2026)
  Shashi Kumar et al.
  5.01
• When the Judge Changes, So Does the Measurement: Auditing LLM-as-Judge Reliability (2026)
  Zongyou Yang et al.
  5.01
• Conceptual Networks for Cross-Linguistic Idiomatic Expressions: A Feature-Based Graph Approach (2026)
  Kiran Pala et al.
  5.01
• STEC: Evidence Compression for Deep Search in Open-domain Multi-Hop QA (2026)
  Xinkang Li et al.
  5.01
• AutoIndex: Learning Representation Programs for Retrieval (2026)
  Sam O'Nuallain et al.
  5.01
• Measuring Reward-Seeking via Contrastive Belief Updates (2026)
  Axel H{\o}jmark et al.
  5.01
• Prompt Design at Scale: How Format, Instruction Count, and Context Length Shape Instruction Adherence and Hallucination in Large Language Models (2026)
  Netanel Eliav
  5.00
• Black-Box Inference of LLM Architectural Properties with Restrictive API Access (2026)
  Christopher Ellis et al.
  4.39
• Automated grading of Linux/bash examinations using large language models: a four-level cognitive taxonomy approach (2026)
  Manuel Alonso-Carracedo et al.
  4.39
• Decision Protocols in Multi-Agent Large Language Model Conversations (2026)
  Lars Benedikt Kaesberg
  4.39
• EvalLoop: A Methodology for Evaluation-Driven Iterative Improvement of Business AI Systems (2026)
  Kenneth Benavides et al.
  4.39
• Memory in the Loop: In-Process Retrieval as ExtendedWorking Memory for Language Agents (2026)
  Yusuf Khan et al.
  4.39
• DT-Guard: Intent-Driven Reasoning-Active Training for Reasoning-Free LLM Safety Guardrail (2026)
  He Liu et al.
  4.39
• Towards Efficient Large Language Model Serving: A Survey on System-Aware KV Cache Optimization (2026)
  Jiantong Jiang et al.
  4.39
• Format Sensitivity Index: Token-Controlled Prompt Wrapper Robustness and Schema Compliance in LLM Benchmarking (2026)
  Deep Pankajbhai Mehta
  4.39
• Interpreting Latent CoT Reasoning as Dynamical Systems (2026)
  Sabari Iyyappan Duraipandian et al.
  4.39
• The Verifier is the Curriculum: Execution-Gated Self-Distillation for Cross-Family Game Generation (2026)
  Chenyu Zhou et al.
  4.39
• Coresets Before Score Sets: Evaluation-Unsupervised Prompt Subset Selection for LLM Benchmarks (2026)
  Jihan Yao et al.
  4.39
• RSLoRA: Training-free Rank Allocation for LoRA via Representational Sensitivity Probing (2026)
  Jiaqi Liu et al.
  4.39
• Agentic Context Learning with Self-Discovered Specification (2026)
  Jike Zhong et al.
  4.39
• Workload-Driven Optimization for On-Device Real-Time Subtitle Translation (2026)
  Tsz-To Wong
  4.39
• AgentAbstain: Do LLM Agents Know When Not to Act? (2026)
  Xun Liu et al.
  4.39
• Efficiently Adapting Spoken Language Models for the Singaporean Context (2026)
  Ng Jia Sheng Jason
  4.39
• Minionese: Comprehensive Benchmark and Mechanistic Study of Multilingual LLM Safety (2026)
  Chigozirim Ifebi et al.
  4.39
• EmoStyle: Affective Conditioning of Style-Specialist Experts for Emotional Image Generation (2026)
  Dexiang Hong et al.
  4.39
• Reinforcement Learning with Verifiable Physics: Post-training LLMs with Continuous Rewards (2026)
  Pengfei Cai et al.
  4.39
• CRiT-QA: Evaluating Multi-hop Reasoning with Counterfactual Chains and Distractor Traps (2026)
  JungMin Yun et al.
  4.39
• PromptGraph: Graph-Guided Prompt Sanitization for Balancing Privacy and Utility in LLM Inference (2026)
  Chen Gu et al.
  4.39
• Abstractiveness Metrics for Evaluating Text Summarization: A Refined Formulation with Empirical Validation (2026)
  Praveenkumar Katwe et al.
  4.39
• SVR-R1: Bootstrapping Multi-modal Reasoning with Self-verification in Reinforcement Learning (2026)
  Mingyuan Wu et al.
  4.39
• Can a Language Model Learn Facts Continually in Its Weights? (2026)
  Charles O'Neill
  4.39
• Verifier-Guided Twelve-Tone Composition: A Generate-Verify-Repair Harness for Symbolic Music Generation (2026)
  Congren Dai et al.
  4.39
• The Ebb and Flow of Multimodal Focus: Scheduling Visual Relay Windows for Grounded VLM Reasoning (2026)
  Wencheng Ye et al.
  4.39
• Comparative Analysis of GAT and BERT for Human-Like Playtesting (2026)
  Kleio Fragkedaki et al.
  4.39
• MUX: Continuous Reasoning via Multiplexed Tokens (2026)
  Ayhan Suleymanzade et al.
  4.39
• One Student, Many Teachers: Multi-Task On-Policy Distillation via Soft-Prompt Privileged Context (2026)
  Yingzi Ma et al.
  4.39
• Binding Drift in Multi-Step Tool-Augmented Agents (2026)
  Rahul Suresh Babu et al.
  4.39
• EmoEUS: Uncertainty Supervision for Multimodal Emotion Recognition in Conversation (2026)
  Zilong Huang et al.
  4.39
• CANDOR: Chance-Calibrated Discordance in Frozen Foundation Encoders (2026)
  Soroosh Tayebi Arasteh et al.
  4.39
• Mark, Don't Erase: Token Inoculation for Dual-Use Knowledge in LLMs (2026)
  Seunghyun Lee et al.
  4.39
• Is EEG-to-Text Feasible in Real-World Scenarios? An In-Depth Analysis Using a Neuropsychology-Inspired Benchmark (2026)
  Zihan Zhang (Research Center for Social Computing and Interactive Robotics et al.
  4.39
• AI Tour Meeting: Group Travel Planning by LLM Agents (2026)
  Daisuke Kikuta
  4.39
• HindsightBench: A Black-Box Behavioral Audit Protocol for Parametric Hindsight in Time-Indexed LLM Decision Tasks (2026)
  Haozhe Jia
  4.39
• Beyond Score Prediction: LLM-Based Essay Scoring and Feedback Generation via Reinforcement Learning with Rubric Rewards (2026)
  Xuefeng Jin et al.
  4.39
• AdaFlash: Adaptive Speculative Decoding via On-Policy Distilled Diffusion Drafters (2026)
  Yu-Yang Qian et al.
  4.39
• CircuitKIT : Circuit Discovery, Evaluation, and Application Toolkit for Mechanistic Interpretability (2026)
  Pratinav Seth et al.
  4.39
• TokenScope: Token-Level Explainability and Interpretability for Code-Oriented Tasks in Large Language Models (2026)
  Amirreza Esmaeili et al.
  3.51
• InfluMatch: Frontier-Quality KOL Search at 4B-Model Cost (2026)
  Krittanon Kaewtawee et al.
  3.51