A focused feed for RLHF, preference data, rater protocols, agent evaluation, and LLM-as-judge research.
Every paper includes structured metadata for quick triage.
Across a diverse benchmark of scaling-law tasks, our method consistently outperforms classical design-based baselines, and often approaches the performance of fitting on the full experimental set while using only about 10% of the total…
Agents that manipulate objects, navigate software, coordinate with others, or design experiments require predictive environment models, yet the term world model carries different meanings across research communities.
Experiments on non-convex benchmark functions and a two-stage stochastic programming problem with quantile neural network surrogates demonstrate that the proposed regularizers can reduce MILP solve times by up to four orders of magnitude…
Evaluation across 8,276 breaths demonstrates high reconstruction accuracy (mean squared error < 0.001 for four-component models) and robust parameter precision under moderate noise.
Humanity's Last Exam (HLE) has become a widely used benchmark for evaluating frontier large language models on challenging, multi-domain questions.
However, community-led analyses have raised concerns that HLE contains a non-trivial number of noisy items, which can bias evaluation results and distort cross-model comparisons.
We introduce the AI Productivity Index for Agents (APEX-Agents), a benchmark for assessing whether AI agents can execute long-horizon, cross-application tasks created by investment banking analysts, management consultants, and corporate…
We test eight agents for the leaderboard using Pass@1.
We introduce Whisper: Courtside Edition, a novel multi-agent large language model (LLM) pipeline that enhances Whisper transcriptions without retraining.
The pipeline intercepts Whisper's initial transcript, applies specialized LLM agents for domain context identification, named entity recognition, and jargon detection, and generates compact prompts that guide Whisper's decoder.
Furthermore, we build JurisMM, a large dataset with over 100,000 recent Chinese judicial records, including both text and multimodal video-text data, enabling comprehensive evaluation.
Experiments on JurisMM and the benchmark LawBench validate our framework's effectiveness.
Vichara surpasses existing judgment prediction benchmarks on both datasets, with GPT-4o mini achieving the highest performance (F1: 81.5 on PredEx, 80.3 on ILDC_expert), followed by Llama-3.1-8B.
Human evaluation of the generated explanations across Clarity, Linking, and Usefulness metrics highlights GPT-4o mini's superior interpretability.
To address this, we present CircuitLM, a multi-agent pipeline that translates user prompts into structured, visually interpretable CircuitJSON schematics.
To systematically assess performance, we deploy a rigorous dual-layered evaluation methodology: a deterministic Electrical Rule Checking (ERC) engine categorizes topological faults by strict severity (Critical, Major, Minor, Warning), while…
Large language model (LLM) agents are moving beyond prompting alone.
ChatGPT marked the rise of general-purpose LLM assistants, DeepSeek showed that on-policy reinforcement learning with verifiable rewards can improve reasoning and tool use, and OpenClaw highlights a newer direction in which agents…
In blind pairwise evaluations by 28 MFA-trained readers and 516 college-educated general readers, AI text from in-context prompting was strongly disfavored by MFA readers for stylistic fidelity (OR=0.16) and quality (OR=0.13), while general…
Fine-tuning ChatGPT on authors' complete works reversed these results: MFA readers favored AI for fidelity (OR=8.16) and quality (OR=1.87), with general readers showing even stronger preference (fidelity OR=16.65; quality OR=5.42).
Through a systematic analysis with human verification, we establish a taxonomy of these failure modes, identifying patterns like Miracle Steps-abrupt jumps to a correct output without a valid preceding derivation.
When integrated into an RL pipeline, RRM-based training consistently outperforms outcome-only supervision across four math benchmarks.
This study reveals a critical safety blind spot in modern LLMs: learning-style queries, which closely resemble ordinary educational questions, can reliably elicit harmful responses.
In addition, the assessment of defenses on the constructed safe prompts reveals inherent limitations of LLMs' safety mechanisms and flaws in the defense methods.
LLM-based agents execute real-world workflows via tools and memory.
We introduce STING (Sequential Testing of Illicit N-step Goal execution), an automated red-teaming framework that constructs a step-by-step illicit plan grounded in a benign persona and iteratively probes a target agent with adaptive…
By sampling annotators from police-affiliated, justice-system-impacted, and non-affiliated Los Angeles residents, we enable the systematic study of perceptual differences across diverse communities.
To this end, we (i) develop a domain-specific evaluation rubric grounded in procedural justice theory, LAPD training materials, and extensive fieldwork; (ii) introduce a rubric-driven preference data construction framework for…
We present L-MARS (Legal Multi-Agent Workflow with Orchestrated Reasoning and Agentic Search), a multi-agent retrieval framework for grounded legal question answering that decomposes queries into structured sub-problems, retrieves evidence…
We introduce LegalSearchQA, a 50-question benchmark across five legal domains whose answers depend on recent developments that post-date model training data.
Transcripts produced via automatic speech recognition (ASR) assign anonymous speaker labels (e.g., Speaker_1), preventing models from capturing consistent human behavior.
Turing-style human evaluations show our simulations are often indistinguishable from real deliberations, providing a practical and scalable method for complex realistic civic simulations.