The authors create the first large-scale dataset and taxonomy of failure modes in multi-agent LLM systems to explain their limited performance gains.
super hub Mixed citations
Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
Mixed citation behavior. Most common role is background (47%).
210
Pith papers citing it
Background
47% of classified citations
abstract
Evaluating large language model (LLM) based chat assistants is challenging due to their broad capabilities and the inadequacy of existing benchmarks in measuring human preferences. To address this, we explore using strong LLMs as judges to evaluate these models on more open-ended questions. We examine the usage and limitations of LLM-as-a-judge, including position, verbosity, and self-enhancement biases, as well as limited reasoning ability, and propose solutions to mitigate some of them. We then verify the agreement between LLM judges and human preferences by introducing two benchmarks: MT-bench, a multi-turn question set; and Chatbot Arena, a crowdsourced battle platform. Our results reveal that strong LLM judges like GPT-4 can match both controlled and crowdsourced human preferences well, achieving over 80% agreement, the same level of agreement between humans. Hence, LLM-as-a-judge is a scalable and explainable way to approximate human preferences, which are otherwise very expensive to obtain. Additionally, we show our benchmark and traditional benchmarks complement each other by evaluating several variants of LLaMA and Vicuna. The MT-bench questions, 3K expert votes, and 30K conversations with human preferences are publicly available at https://github.com/lm-sys/FastChat/tree/main/fastchat/llm_judge.
hub tools
citation-role summary
background 15
method 10
dataset 4
baseline 1
citation-polarity summary
claims ledger
- abstract Evaluating large language model (LLM) based chat assistants is challenging due to their broad capabilities and the inadequacy of existing benchmarks in measuring human preferences. To address this, we explore using strong LLMs as judges to evaluate these models on more open-ended questions. We examine the usage and limitations of LLM-as-a-judge, including position, verbosity, and self-enhancement biases, as well as limited reasoning ability, and propose solutions to mitigate some of them. We then verify the agreement between LLM judges and human preferences by introducing two benchmarks: MT-be
authors
co-cited works
representative citing papers
ORPO performs preference alignment during supervised fine-tuning via a monolithic odds ratio penalty, allowing 7B models to outperform larger state-of-the-art models on alignment benchmarks.
LongBench is the first bilingual multi-task benchmark for long context understanding in LLMs, containing 21 datasets in 6 categories with average lengths of 6711 words (English) and 13386 characters (Chinese).
Gradient and greedy search over token suffixes produces universal, transferable adversarial prompts that elicit objectionable outputs from aligned models including black-box commercial systems.
Analysis of 500k ChatGPT logs shows over one-third of conversations generate fiction, dominated by power users with repetitive and niche patterns.
Low-resource safety failures are action failures because the harmfulness representation transfers but the decision calibration does not; this is fixed by recalibrating a high-resource gate with 1-4 target-language examples.
RWGBench is a citation-centric benchmark for related work generation built from 40k CS papers and a 100-paper test set, with multi-dimensional metrics that better match human expert judgment than standard similarity scores.
Introduces (ε,q,t,A)-behavioral indistinguishability and shows via Qwen/Llama experiments that LoRA distillation boosts semantic similarity but leaves detectable behavioral differences under adversarial evaluation.
A Behavioral Specification interpretive layer improves representational accuracy for AI personalization by compressing user data into patterns, outperforming raw corpora and commercial memory systems on held-out behavioral predictions across 14 autobiographical corpora while reducing context cost.
OR-Space is a benchmark for LLM agents performing full-lifecycle optimization tasks across Build, Revise, and Explain modes in executable multi-artifact workspaces.
Self-evolving rubric with anti-gaming fitness reveals that objective capability scaling fails to transfer to subjective LLM behaviors, with advice-restraint as the universal lowest dimension that can regress.
LogDx-CI benchmark shows hybrid grep+tail reducers achieve top diagnosis quality at low cost, agent loops shrink quality variance across reducers, and cross-family LLM summarizers outperform same-family pairs.
LLMs show severe staleness after training cutoffs and recency bias on historical German statutes; RAG with version filtering mitigates both better than web search.
A multi-agent pipeline iteratively refines topology optimization outputs to match natural language preferences for branched structures, achieving 60% success rate across replicates in cantilever and phone-stand tasks.
Introduces the stochastic-deterministic boundary (SDB) as a load-bearing primitive for LLM agent runtimes and provides a five-step methodology plus catalog of six patterns adapted from distributed systems.
DecisionBench supplies a fixed task suite, model pool, delegation interface, and multi-axis metrics to evaluate emergent delegation, showing similar quality across awareness conditions but 15-31 point headroom under perfect delegation.
SCICONVBENCH is a new benchmark evaluating LLMs on multi-turn disambiguation and inconsistency resolution for task formulation in computational science, with frontier models reaching only 52.7% success on fluid mechanics disambiguation cases.
CBEA with LCV bounds evidence sets and validates commitments before response generation, achieving zero failures in scoped tests at 0.49-0.60 availability versus near-zero for baselines.
Belief Engine is a configurable belief-update mechanism for multi-agent LLM systems that uses structured argument extraction and log-odds stance updates to make evidence-grounded deliberation inspectable and controllable.
Test-Time Hinting trains a hint generator to prepend contextual guidance to VLM prompts, improving accuracy on natural-image VQA benchmarks with generalization to unseen tasks and models.
Presents a likelihood-based benchmark for equation-suffix prediction in technical papers with controls to detect shortcut vulnerabilities in model forecasts.
LLM multi-agent systems on lattices show bias-driven order-disorder crossovers instead of true phase transitions, with extracted effective couplings and fields serving as model-specific fingerprints.
SlimSpec replaces the standard LM-head in draft models with a low-rank version to deliver 4-5x faster speculative decoding while preserving full vocabulary and competitive acceptance rates.
ProactBench measures LLM conversational proactivity in three phases using 198 multi-agent dialogues and finds recovery behavior hard to predict from existing benchmarks.
citing papers explorer
-
Decodable but Not Corrected by Fixed Residual-Stream Linear Steering: Evidence from Medical LLM Failure Regimes
Overthinking in medical QA is linearly decodable at 71.6% accuracy yet fixed residual-stream steering yields no correction across 29 configurations, while enabling selective abstention with AUROC 0.610.
-
Why Expert Alignment Is Hard: Evidence from Subjective Evaluation
Expert alignment in subjective LLM evaluations is difficult because expert judgments are heterogeneous, partly tacit, dimension-dependent, and temporally unstable.
-
From Experimental Limits to Physical Insight: A Retrieval-Augmented Multi-Agent Framework for Interpreting Searches Beyond the Standard Model
HEP-CoPilot is a new multi-agent retrieval framework that retrieves, reconstructs, and compares experimental limits from HEP literature and HEPData to support interpretation of beyond-Standard-Model searches.
-
Position: Safety and Fairness in Agentic AI Depend on Interaction Topology, Not on Model Scale or Alignment
In agentic AI, safety and fairness are governed by interaction topology rather than model scale or alignment.
-
Agent-Agnostic Evaluation of SQL Accuracy in Production Text-to-SQL Systems
STEF is a schema-agnostic evaluation framework that scores SQL generation accuracy from natural language inputs using semantic feature alignment and a composite metric.
-
ChipLingo: A Systematic Training Framework for Large Language Models in EDA
ChipLingo trains LLMs on EDA data via corpus construction, domain-adaptive pretraining, and RAG scenario alignment, reaching 59.7% accuracy with an 8B model and 70.02% with a 32B model on a new internal EDA benchmark.
-
GS-Quant: Granular Semantic and Generative Structural Quantization for Knowledge Graph Completion
GS-Quant generates coarse-to-fine discrete codes for KG entities via semantic hierarchy injection and causal sequence reconstruction, enabling LLMs to perform knowledge graph completion by treating the codes as vocabulary tokens.
-
Cross-Model Consistency of AI-Generated Exercise Prescriptions: A Repeated Generation Study Across Three Large Language Models
Three LLMs exhibit distinct consistency profiles in repeated exercise prescription generation, with GPT-4.1 producing unique but semantically stable outputs while Gemini 2.5 Flash achieves high similarity through text duplication.
-
Bridging the Reasoning Gap in Vietnamese with Small Language Models via Test-Time Scaling
SFT on localized Vietnamese math data improves explanation quality by 77% in a 1.7B model, with CoT+self-consistency outperforming ReAct-style test-time scaling.
-
Evaluating Multimodal LLMs for Inpatient Diagnosis: Real-World Performance, Safety, and Cost Across Ten Frontier Models
Multimodal LLMs performed similarly across models and better than standard care on diagnostic accuracy and patient safety in a real-world LMIC hospital dataset.
-
Adaptive Query Routing: A Tier-Based Framework for Hybrid Retrieval Across Financial, Legal, and Medical Documents
Tree reasoning outperforms vector search on complex document queries but a hybrid approach balances results across tiers, with validation showing an 11.7-point gap on real finance documents.
-
AlphaEval: Evaluating Agents in Production
AlphaEval is a benchmark of 94 production-sourced tasks from seven companies for evaluating full AI agent products across six domains using multiple judgment methods, plus a framework to build similar benchmarks.
-
Retrieval Is Not Enough: Why Organizational AI Needs Epistemic Infrastructure
OIDA is a proposed framework that represents organizational knowledge as epistemic Knowledge Objects with class-specific importance decay and signed contradictions, plus a QUESTION mechanism that surfaces modeled ignorance via inverse decay.
-
From Hallucination to Structure Snowballing: The Alignment Tax of Constrained Decoding in LLM Reflection
Enforcing structured reflection via Outlines-based constrained decoding on an 8B LLM triggers structure snowballing instead of better self-correction, producing near-perfect syntax but persistent semantic errors and revealing an alignment tax.
-
From Incomplete Architecture to Quantified Risk: Multimodal LLM-Driven Security Assessment for Cyber-Physical Systems
ASTRAL applies multimodal LLMs with prompt chaining and few-shot learning to synthesize CPS architectures from disparate sources, enabling adaptive threat identification and quantitative risk estimation, as supported by ablation studies and feedback from 14 cybersecurity practitioners.
-
Breakdowns in Conversational AI: Interactional Failures in Emotionally and Ethically Sensitive Contexts
Mainstream conversational models show escalating affective misalignments and ethical guidance failures during staged emotional trajectories, organized into a taxonomy of interactional breakdowns.
-
Evaluating AI-Generated Images of Cultural Artifacts with Community-Informed Rubrics
Case studies with blind UK residents and people from Kerala and Tamil Nadu demonstrate that community input at the systematization stage produces culturally grounded definitions of appropriateness for text-to-image model outputs.
-
RAG-DIVE: A Dynamic Approach for Multi-Turn Dialogue Evaluation in Retrieval-Augmented Generation
RAG-DIVE uses an LLM to dynamically generate, validate, and evaluate multi-turn dialogues for assessing RAG system performance in interactive settings.
-
PEFT-Factory: Unified Parameter-Efficient Fine-Tuning of Autoregressive Large Language Models
PEFT-Factory supplies a ready-to-use, extensible codebase that unifies 19 PEFT methods and evaluation pipelines for fine-tuning large autoregressive language models.
-
Patching LLM Like Software: A Lightweight Method for Improving Safety Policy in Large Language Models
Prepending a compact learnable prefix to LLMs produces safety gains comparable to next-generation aligned models while preserving fluency and adding negligible parameters.
-
ASTRA: An Automated Framework for Strategy Discovery, Retrieval, and Evolution for Jailbreaking LLMs
ASTRA is an automated closed-loop framework that discovers, retrieves, and evolves jailbreak attack strategies for LLMs using a dynamic three-tier strategy library and outperforms baselines in black-box settings.
-
MARS-SQL: A multi-agent reinforcement learning framework for Text-to-SQL
MARS-SQL trains a multi-agent RL system with ReAct-style interaction and generative validation to produce SQL queries, reaching 77.84% execution accuracy on BIRD dev and 89.75% on Spider test.
-
HFX: Joint Design of Algorithms and Systems for Multi-SLO Serving and Fast Scaling
HFX jointly designs scheduling and scaling for multi-SLO LLM serving, achieving up to 4.44x higher SLO attainment, 65.82% lower latency, and 49.81% lower cost than prior systems on multi-task workloads.
-
Mitigating Hallucination in Large Vision-Language Models via Adaptive Attention Calibration
CAAC mitigates hallucinations in LVLMs via Visual-Token Calibration and Adaptive Attention Re-Scaling guided by model confidence, showing gains on CHAIR, AMBER, and POPE especially in long-form generation.
-
WildFeedback: Aligning LLMs With In-situ User Interactions And Feedback
WildFeedback extracts preference pairs from in-situ user feedback in LLM conversations to fine-tune models for better alignment with real user preferences.
-
World Model on Million-Length Video And Language With Blockwise RingAttention
Presents open-source 7B models for million-token video and language understanding via Blockwise RingAttention, setting new benchmarks in retrieval and long video tasks.
-
Mixtral of Experts
Mixtral 8x7B is a sparse MoE LLM activating 2 of 8 experts per layer that matches or exceeds Llama 2 70B and GPT-3.5 on benchmarks while using only 13B active parameters.
-
MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices
MobileVLM achieves on-par performance with much larger vision-language models on standard benchmarks while delivering state-of-the-art inference speeds of 21.5 tokens per second on Snapdragon 888 CPU and 65.3 on Jetson Orin GPU.
-
InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks
InternVL scales a vision model to 6B parameters and aligns it with LLMs using web data to achieve state-of-the-art results on 32 visual-linguistic benchmarks.
-
AppAgent: Multimodal Agents as Smartphone Users
AppAgent lets large language models operate diverse smartphone apps via visual interactions and learns app usage from exploration or demonstrations.
-
Search Discipline for Long-Horizon Research Agents
Aggregate metrics in research agents can invert rankings when validity is disaggregated, demonstrated on an ecosystem model task, motivating an external audit protocol over agent self-decision.
-
ImmigrationQA: A Source-Grounded Dataset and Small-Model Adaptation for U.S. Immigration Law
A new source-grounded QA dataset for U.S. immigration law is built from official documents and used to fine-tune a 3B model, yielding a 27% mean score improvement over the base model on a held-out sample.
-
Domain Adaptation and Reasoning Frameworks in Language Models: A Controlled Experiment with Historical Cosmology
Fine-tuning on historical cosmology data reshapes language model explanatory frameworks, leading to stance changes as a secondary effect from regime redistribution.
-
Opir: Efficient Multi-Task Safety Classification for Toxicity, Jailbreaks, Hate Speech, and Harmful Content
Opir introduces efficient multi-task encoder models trained on a 996-category safety taxonomy that match or exceed larger baselines on most safety benchmarks while using under 100M parameters for edge variants.
-
Refining and Reusing Annotation Guidelines for LLM Annotation
An iterative moderation framework refines and reuses annotation guidelines to improve LLM annotation accuracy on biomedical NER tasks across GPT, Gemini, and DeepSeek models.
-
From Text to DSL: Evaluating Grammar-Based Model Generation Using Open LLMs
Compact open-source LLMs can produce syntactically valid, semantically complete, and inter-model consistent DSL models from text via few-shot prompting, with some 7B-12B models matching much larger ones in quality.
-
The Single-File Test: A Longitudinal Public-Interface Evaluation of First-Output LLM Web Generation with Social Reach Tracking
Claude outperformed other LLM families in generating functional single-file HTML under fixed public conditions, but neither technical variables nor prompt details reliably predicted 24-hour social media impressions.
-
Terminus-4B: Can a Smaller Model Replace Frontier LLMs at Agentic Execution Tasks?
A fine-tuned 4B model matches or exceeds frontier LLMs in terminal execution subagent tasks for coding agents, reducing main agent token usage by 30% with no performance loss.
-
Is Vibe Coding the Future? An Empirical Assessment of LLM Generated Codes for Construction Safety
LLM vibe-coded safety scripts achieve ~85% execution success but suffer ~45% silent failure rate in safety logic, with GPT-4o-Mini inaccurate in ~56% of working cases.
-
Scalable and Personalized Oral Assessments Using Voice AI
Viva conducts voice-based oral exams and grades transcripts with a multi-LLM panel; tested on two small NYU cohorts at under $1 per exam while surfacing five implementation patterns from observed failures.
-
Personalized AI Practice Replicates Learning Rate Regularity at Scale
Large-scale data from an AI platform confirms students have consistent learning rates (IQR 7.01-8.25 opportunities to 80% mastery) despite variable starting knowledge, replicating prior findings with automated knowledge components.
-
Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
Gemini 2.5 Pro and Flash models are presented as achieving frontier performance in reasoning, coding, and long-context multimodal tasks while spanning a cost-capability Pareto curve.
-
Sensorimotor Self-Recognition in Multimodal Large Language Model-Driven Robots
Multimodal LLMs in robots develop self-identification and predictive awareness through sensorimotor loops, with structural equation modeling linking sensory integration to dimensions of the minimal self.
-
Seed1.5-VL Technical Report
Seed1.5-VL is a compact multimodal model that sets new records on dozens of vision-language benchmarks and outperforms prior systems on agent-style tasks.
-
LLMOrbit: A Circular Taxonomy of Large Language Models -From Scaling Walls to Agentic AI Systems
A survey taxonomy of LLMs identifies three scaling crises and six efficiency paradigms while tracing the shift from generation to tool-using agents.
-
Towards EnergyGPT: A Large Language Model Specialized for the Energy Sector
Fine-tuned LLaMA 3.1-8B variants for the energy sector outperform the base model on domain QA benchmarks, with LoRA delivering similar gains at lower training cost.
-
Fairness in Multi-Agent Systems for Software Engineering: An SDLC-Oriented Rapid Review
A rapid review of fairness in LLM-enabled multi-agent systems for the software development lifecycle concludes that the field lacks standardized evaluations, broad coverage, and effective governance, leaving it unprepared for deployable fair systems.
-
OpenCLAW-P2P v7.0-P2PCLAW: Resilient Multi-Layer Persistence, Live Reference Verification, and Production-Scale Evaluation of Decentralized AI Peer Review v7.0 -- Mathematical Corrections & Ecosystem Developments Edition
OpenCLAW-P2P v7.0 adds mathematical corrections for dimensional consistency and range constraints plus ecosystem expansions including new 4B/9B parameter models to a decentralized AI peer-review platform that claims >85% accuracy on fabricated citation detection.
- Insights Generator: Systematic Corpus-Level Trace Diagnostics for LLM Agents
- Internalizing Tool Knowledge in Small Language Models via QLoRA Fine-Tuning