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%).
283
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.
FARS deployed at scale produced 166 AI/ML papers across 67 topics that received 282 structured human reviews indicating some review-worthy outputs alongside recurring failure modes.
The paper presents EMPATH, a new multilingual multi-turn benchmark for safety evaluation of emotional-support chatbots that uses separate auditor and judge models and releases its pipeline and rubrics.
CLQT is a new closed-loop, cost-aware benchmark that diagnoses LLM trading agent capabilities through strategy-consistent metrics and hash-verifiable trails rather than outcome rankings.
Analysis of 500k ChatGPT logs shows over one-third of conversations generate fiction, dominated by power users with repetitive and niche patterns.
Introduces the Power Systems Agent Benchmark with 41 task families across eight power engineering areas for executable evaluation of AI agents using deterministic feasibility checks.
User facts are internalized as surgical local edits to a hash-keyed Engram memory table with reasoning skill held in a shared adapter, claimed to match LoRA recall, improve indirect reasoning 5.6x on average, and compose across users with 33,000x smaller footprint than per-user adapters.
Wall-clock leaky-integrator monitors on variable-cadence agent streams exhibit a sharp cliff between constant-alarm and silent regimes, while sample-time CUSUM monitors remain invariant; transition detection avoids the trap.
RealMath-Eval benchmark shows LLM judges have an evaluation gap, performing worse on diverse real human math reasoning than on synthetic solutions due to greater error diversity and higher surprisal.
The paper defines Cherry-pick Override (CCO) as unauthorized directional commitment by LLM judges under mixed evidence and quantifies its prevalence (>84% on AVeriTeC conflicting subset) while testing intervention ladders and a two-channel reference probe.
MAC-Bench is a new adversarial benchmark that converts legal texts into executable scenarios via the SERV pipeline to measure procedural compliance in multi-agent LLM systems using CSR and MG metrics.
LLM judges exhibit high stability under neutral re-evaluation but substantial reversibility under targeted post-decision challenges, quantified via a new Evaluation Robustness Score (ERS).
CoEval generates task-specific benchmarks by rotating models through teacher, student, and judge roles, then weights questions by discriminative power and judges by panel consensus to recover accurate model rankings without labels.
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.
MuCRASP prunes VLMs in a CoT-aware manner, outperforming baselines by preserving reasoning quality at 30-50% compression rates on models like Qwen2.5-VL-7B.
citing papers explorer
-
Why Do Multi-Agent LLM Systems Fail?
The authors create the first large-scale dataset and taxonomy of failure modes in multi-agent LLM systems to explain their limited performance gains.
-
VLegal-Bench: Cognitively Grounded Benchmark for Vietnamese Legal Reasoning of Large Language Models
VLegal-Bench supplies 10,450 expert-validated samples for evaluating LLMs on Vietnamese legal questions, retrieval, multi-step reasoning, and scenario solving.
-
Evalet: Evaluating Large Language Models through Functional Fragmentation
Evalet applies functional fragmentation to deliver fragment-level qualitative analysis of LLM evaluations, with a user study showing 48% more misalignment detections than holistic scoring.
-
LLMs Judging LLMs: A Simplex Perspective
A simplex geometry framework shows when LLM-as-judge rankings are identifiable, provides a basis for preferring binary over multi-level scoring, and uses Bayesian priors to model epistemic uncertainty about judges.
-
TF1-EN-3M: Three Million Synthetic Moral Fables for Training Small, Open Language Models
The authors generate and publicly release the first large-scale open dataset of three million structured moral fables produced by small open language models together with a reproducible LLM-judge evaluation pipeline.
-
PRIMETIME : Limits of LLMs in Temporal Primitives
PRIMETIME generator reveals that LLM datetime parsing and arithmetic primitives are individually unreliable but fully learnable via fine-tuning, enabling frontier-level accuracy on event planning with small LoRA models.
-
Response-Based Knowledge Distillation for Multilingual Jailbreak Prevention Unwittingly Compromises Safety
Distilling safe refusal behavior from OpenAI o1-mini into Llama-3, Gemma-2, and Qwen3 models via response-based LoRA on multilingual jailbreak data increases jailbreak success rates on MultiJail by up to 16.6 points.
-
Reading Between the Lines: The One-Sided Conversation Problem
The one-sided conversation problem is introduced with empirical results showing that future-turn access and utterance length improve missing-turn reconstruction while high-quality summaries are possible without reconstruction on standard dialogue datasets.
-
LLM Prompt Duel Optimizer: Efficient Label-Free Prompt Optimization
Prompt Duel Optimizer uses dueling bandits and LLM-as-judge pairwise feedback with Double Thompson Sampling and top-performer mutation to find stronger prompts than label-free baselines on BBH and MS MARCO under limited comparison budgets.
-
Don't Pass@k: A Bayesian Framework for Large Language Model Evaluation
A Dirichlet-prior Bayesian estimator for model success probability replaces Pass@k, delivering faster-converging and more stable rankings with credible intervals on math benchmarks.
-
QuiLL: An LLM-Based Vulnerability Assessment Framework for the Wild
QuiLL is a new evaluation pipeline that uses optimized LLM prompts, dynamic in-context learning from an NVD vector store, and a novel accuracy-plus-reasoning metric to benchmark vulnerability detection in real code.
-
Efficient and Transferable Agentic Knowledge Graph RAG via Reinforcement Learning
KG-R1 trains a single RL agent to retrieve from and reason over knowledge graphs in one loop, achieving higher accuracy with fewer tokens than multi-module baselines and transferring to unseen graphs.
-
Fin-PRM: A Domain-Specialized Process Reward Model for Financial Reasoning in Large Language Models
Fin-PRM is a domain-specialized process reward model that supplies binary step-level and trajectory-level supervision signals for financial reasoning in LLMs and outperforms general PRMs on CFLUE and FinQA benchmarks.
-
Listener-Rewarded Thinking in VLMs for Image Preferences
Listener-augmented GRPO uses an independent frozen VLM to provide dense confidence scores on reasoning traces, yielding 67.4% accuracy on ImageReward, up to +6% OOD gains on 1.2M-vote human data, and fewer reasoning contradictions.
-
DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents
DeepResearch Bench supplies 100 expert-crafted PhD-level tasks and two human-aligned evaluation frameworks to measure deep research agents on report quality and citation accuracy.
-
Latent Trajectory Dynamics in Large Language Models: A Manifold Evolution Framework with Empirical Validation
DMET models LLM generation as controlled dynamical trajectories on a semantic manifold, with three proxy metrics that predict output quality and support adaptive decoding to lower perplexity.
-
Tuning Language Models for Robust Prediction of Diverse User Behaviors
BehaviorLM applies progressive fine-tuning in two stages to let LLMs predict both frequent anchor and rare tail user behaviors more robustly on real-world datasets.
-
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.
-
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.
-
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.
- Aligning Deep Implicit Preferences by Learning to Reason Defensively
- Are Large Pre-trained Vision Language Models Effective Construction Safety Inspectors?