This has consequences for digital humanities and computational text analysis, where features such as function words, pronouns, contractions, and punctuation often serve as evidence for style, voice, authorship, and corpus integrity.
Tharindu Kumarage, Lisa Bauer, Yao Ma, Dan Rosen, Yashasvi Raghavendra Guduri, Anna Rumshisky · Apr 23, 2026 · Citations: 0
Rubric RatingGeneral
To address this gap, we introduce ESRRSim, a taxonomy-driven agentic framework for automated behavioral risk evaluation.
Evaluation across 11 reasoning LLMs reveals substantial variation in risk profiles (detection rates ranging 14.45%-72.72%), with dramatic generational improvements suggesting models may increasingly recognize and adapt to evaluation…
The transition from stateless language model inference to persistent, multi session autonomous agents has revealed memory to be a primary architectural bottleneck in the deployment of production grade agentic systems.
Through systematic benchmarking on the LongMemEval and LoCoMo evaluation suites, Memanto achieves state of the art accuracy scores of 89.8 percent and 87.1 percent respectively.
The growth of agentic AI has drawn significant attention to function calling Large Language Models (LLMs), which are designed to extend the capabilities of AI-powered system by invoking external functions.
While existing attacks focus on semantic preference of the model for function-calling tasks, we show that FHA is largely agnostic to the context semantics and remains effective across domains and function sets.
Multi-agent systems built from teams of large language models (LLMs) are increasingly deployed for collaborative scientific reasoning and problem-solving.
These systems require agents to coordinate under shared constraints, such as GPUs or credit balances, where cooperative behavior matters.
Aimin Zhang, Jiajing Guo, Fuwei Jia, Chen Lv, Boyu Wang, Fangzheng Li · Apr 22, 2026 · Citations: 0
Llm As JudgeAutomatic MetricsGeneral
Experimental results based on real-world foreign trade scenarios demonstrate that, after integrating EvoAgent, GPT5.2 achieves significant improvements in professionalism, accuracy, and practical utility.
Under a five-dimensional LLM-as-Judge evaluation protocol, the overall average score increases by approximately 28%.
Reinforcement learning (RL) has become a prevalent paradigm for training tool calling agents, which typically requires online interactive environments.
In this work, we propose TRUSTEE, a cost-friendly method for training tool calling agents with dynamic environments fully simulated by free open-source LMs that can be as small as 8B, including task generation, user simulation, tool…
Tiankai Yang, Yi Nian, Xinyuan Li, Ruiyao Xu, Henry Peng Zou, Kaize Ding · Apr 19, 2026 · Citations: 0
Pairwise PreferenceAutomatic MetricsGeneral
Aligning large language models with human preferences must balance two competing goals: responding helpfully to legitimate requests and reliably refusing harmful ones.
Most preference-based safety alignment methods collapse safety into a single scalar that is applied uniformly to every preference pair.
We propose Doc-V^*, an OCR-free agentic framework that casts multi-page DocVQA as sequential evidence aggregation.
Across five benchmarks, Doc-V^* outperforms open-source baselines and approaches proprietary models, improving out-of-domain performance by up to 47.9\% over RAG baseline.
Heming Xia, Yongqi Li, Cunxiao Du, Mingbo Song, Wenjie Li · Apr 15, 2026 · Citations: 0
Automatic MetricsGeneral
Experiments across multiple benchmarks demonstrate that ToolSpec achieves up to a 4.2x speedup, substantially outperforming existing training-free speculative decoding methods.
Yoonsang Lee, Howard Yen, Xi Ye, Danqi Chen · Apr 13, 2026 · Citations: 0
Automatic MetricsGeneral
To address this, we propose AggAgent, an aggregation agent that treats parallel trajectories as an environment.
Across six benchmarks and three model families (GLM-4.7, Qwen3.5, MiniMax-M2.5), AggAgent outperforms all existing aggregation methods-by up to 5.3% absolute on average and 10.3% on two deep research tasks-while adding minimal overhead, as…
LLM evaluations drive which models get deployed, what safety standards get adopted, which research conclusions get published, and how projections of AI's labor-market impact get made.
Using Chatbot Arena data, we show naive 95\% CI coverage drops as n grows while TEE-corrected coverage holds at 95\%, and TEE-guided pipelines restrict the benchmark gaming surface from 56 to 32 Elo (K=27), below the human-leaderboard…
Xiaomeng Hu, Yinger Zhang, Fei Huang, Jianhong Tu, Yang Su, Lianghao Deng · Apr 13, 2026 · Citations: 0
Simulation EnvGeneral
We introduce OccuBench, a benchmark covering 100 real-world professional task scenarios across 10 industry categories and 65 specialized domains, enabled by Language Environment Simulators (LESs) that simulate domain-specific environments…
We evaluate 15 frontier models across 8 model families and find that: (1) no single model dominates all industries, as each has a distinct occupational capability profile; (2) implicit faults (truncated data, missing fields) are harder than…
The advent of agentic multimodal models has empowered systems to actively interact with external environments.
Extensive evaluations demonstrate that our resulting model, Metis, reduces tool invocations by orders of magnitude while simultaneously elevating reasoning accuracy.
Experiments on three multimodal MoE models across six benchmarks demonstrate consistent improvements, with gains of up to 3.17% on complex visual reasoning tasks.
