A focused feed for RLHF, preference data, rater protocols, agent evaluation, and LLM-as-judge research.
Every paper includes structured metadata for quick triage.
Experiments on three multimodal MoE models across six benchmarks demonstrate consistent improvements, with gains of up to 3.17% on complex visual reasoning tasks.
Extensive evaluations across 18 diverse benchmarks demonstrate its superior performance over strong open-source and leading proprietary frontier models.
Experiments on mathematical reasoning benchmarks demonstrate that InfoDensity matches or surpasses state-of-the-art baselines in accuracy while significantly reducing token usage, achieving a strong accuracy-efficiency trade-off.
They further rely on safety alignment strategies via RLHF, system prompts, and output filters to block verbatim regurgitation of copyrighted works, and have cited the efficacy of these measures in their legal defenses against copyright…
AI coding agents can resolve real-world software issues, yet they frequently introduce regressions -- breaking tests that previously passed.
When deployed as an agent skill with a different model and framework, TDAD improved issue-resolution rate from 24% to 32%, confirming that surfacing contextual information outperforms prescribing procedural workflows.
Across language modeling, retrieval, and instruction-following benchmarks, HiCI yields consistent improvements over strong baselines, including matching proprietary models on topic retrieval and surpassing GPT-3.5-Turbo-16K on code…
Agent Control Protocol (ACP) is a formal technical specification for governance of autonomous agents in B2B institutional environments.
ACP acts as an admission control layer between agent intent and system state mutation: before execution, every agent action must pass a cryptographic admission check that validates identity, capability scope, delegation chain, and policy…
Experiments conducted on both a public PV defect benchmark and a private industrial EL dataset demonstrate the effectiveness of the proposed framework.
It surpasses the autonomous baseline by 14.8% and human experts by 4.7% on the public dataset, and by 4.9% and 2.5%, respectively, on the private dataset.
We evaluate the approach on sentiment classification and opinion detection tasks, analyzing changes in inter-annotator agreement and revision behavior.
To quantify these effects, we introduce the Annotator Effort Proxy (AEP), a metric capturing the proportion of labels revised after exposure to reasoning.
LLM-powered agents are emerging as a dominant paradigm for autonomous task solving.
Unlike standard inference workloads, agents operate in a strictly serial "LLM-tool" loop, where the LLM must wait for external tool execution at every step.
Experiments on LLaDA-8B-Instruct and Dream-7B-Instruct show that EntropyCache achieves 15.2\times-26.4\times speedup on standard benchmarks and 22.4\times-24.1\times on chain-of-thought benchmarks, with competitive accuracy and decision…
Multi-Agent Path Finding (MAPF) seeks collision-free paths for multiple agents from their respective start locations to their respective goal locations while minimizing path costs.
Most existing MAPF algorithms rely on a common assumption of synchronized actions, where the actions of all agents start at the same time and always take a time unit, which may limit the use of MAPF planners in practice.
Moreover, since companies typically do not make resumes with evaluation results publicly available, it remains unclear which resume samples should be used during learning to improve an LLM's judgment performance.
These samples are used for in-context learning together with a persona description and evaluation criteria, enabling open-source LLMs to act as a career advisor and evaluate unseen resumes.
Existing jailbreak defence frameworks for Large Vision-Language Models often suffer from a safety utility tradeoff, where strengthening safety inadvertently degrades performance on general visual-grounded reasoning tasks.
In this work, we investigate whether safety and utility are inherently antagonistic objectives.