Zixuan Wang, Yuchen Yan, Hongxing Li, Teng Pan, Dingming Li, Ruiqing Zhang · May 7, 2026 · Citations: 0
Simulation EnvCoding
While long-horizon agentic tasks require language agents to perform dozens of sequential decisions, training such agents with reinforcement learning remains challenging.
BEACON partitions trajectories at milestone boundaries, applies temporal reward shaping within segments to credit partial progress, and estimates advantages at dual scales to prevent distant failures from corrupting the evaluation of local…
Haotian Xia, Hao Peng, Yunjia Qi, Xiaozhi Wang, Bin Xu, Lei Hou · May 6, 2026 · Citations: 0
Pairwise PreferenceAutomatic MetricsCoding
Although large language models (LLMs) have significantly advanced text generation, stories generated by LLMs still diverge from human-authored works regarding complex narrative structure and human-aligned preferences.
We find existing reward models struggle to select human-preferred stories, with the best model achieving only 66.3\% accuracy.
Tianyang Han, Hengyu Shi, Junjie Hu, Xu Yang, Zhiling Wang, Junhao Su · May 5, 2026 · Citations: 0
Rubric RatingAutomatic MetricsMathLaw
Extensive experiments on code and math benchmarks show that this executor-grounded reasoning reward improves the two-stage planner-executor system over execution-only training, suggesting that reasoning supervision should evaluate not only…
Mullosharaf K. Arabov · May 5, 2026 · Citations: 0
Coding
This preprint presents a systematic, research-oriented practicum that guides the reader through the entire modern NLP pipeline --- from tokenisation and vectorisation to fine tuning of large language models, retrieval augmented generation,…
Seventeen hands-on sessions combine concise theory with detailed implementation plans, formalised evaluation metrics, and transparent assessment criteria.
Zihan Lin, Xiaohan Wang, Jie Cao, Jiajun Chai, Li Wang, Xiaodong Lu · May 1, 2026 · Citations: 0
Automatic MetricsMathCoding
ResRL then projects negative-token hidden representations onto an SVD-based low-rank positive subspace and uses projection residuals to modulate negative gradients, improving reasoning while preserving diversity and outperforming strong…
Experiments on Qwen3-VL show that PRISM consistently improves downstream RLVR performance across multiple RL algorithms (GRPO, DAPO, GSPO) and diverse multimodal benchmarks, improving average accuracy by +4.4 and +6.0 points over the…
We present MuDABench, a benchmark for multi-document analytical QA, where questions require extracting and synthesizing information across numerous documents to perform quantitative analysis.
To address these limitations, we propose a multi-agent workflow that orchestrates planning, extraction, and code generation modules.
A model's ability to reliably process these sources is key to system safety.
Our findings reveal general patterns: most models rely more on document assertions than user assertions, and this preference is reinforced by post-training.
To enable systematic study, we unify and formalize safe, helpful, and pedagogical behaviors with a knowledge-mastery graph and introduce SHAPE, a benchmark of 9,087 student-question pairs for evaluating tutoring behavior under adversarial…
Experiments across multiple LLMs show that our method yields significantly improved safety under two pedagogical jailbreak settings, while maintaining near-ceiling helpfulness under the same evaluation protocol.
Emil Ryd, Henning Bartsch, Julian Stastny, Joe Benton, Vivek Hebbar · Apr 23, 2026 · Citations: 0
DemonstrationsMathCoding
As AI systems begin to automate complex tasks, supervision increasingly relies on weaker models or limited human oversight that cannot fully verify output quality.
We present a controlled multidimensional pairwise evaluation framework for multilingual TTS that combines linguistic control with perceptually grounded annotation.
Using 5K+ native and code-mixed sentences across 10 Indic languages, we evaluate 7 state-of-the-art TTS systems and collect over 120K pairwise comparisons from over 1900 native raters.
A key benefit of self-play for post-training LLMs is its minimal supervision costs: self-play avoids the need for high-quality input-output pairs traditionally constructed by humans or expensive proprietary models.
We propose POP, a self-play framework that uses the same LLM to synthesize evaluation rubrics along with each input-output pair.
Yiqun Sun, Pengfei Wei, Lawrence B. Hsieh · Apr 16, 2026 · Citations: 0
Automatic MetricsCoding
We present Corpus2Skill, a system-level retrieval architecture for bounded, structurally coherent corpora such as enterprise knowledge bases: an offline compiler distills the corpus into a hierarchical skill directory, and at serve time an…
On an enterprise customer-support benchmark, Corpus2Skill improves both answer quality and grounding over single-shot dense, hybrid, hierarchical-retrieval, and agentic RAG baselines at a moderate cost tradeoff, and the lead persists under…
Across five model configurations, two families, and three benchmarks, we find that 52--88% of chain-of-thought tokens are produced after the answer is recoverable from a partial prefix.
Komal Kumar, Aman Chadha, Salman Khan, Fahad Shahbaz Khan, Hisham Cholakkal · Apr 7, 2026 · Citations: 0
Automatic MetricsCoding
Recent advances in multi-agent large language models (LLMs) have demonstrated strong potential for understanding user intent and are being trained to utilize various tools.
In this paper, we introduce Paper Circle, a multi-agent research discovery and analysis system designed to reduce the effort required to find, assess, organize, and understand academic literature.
While structured feedback can mitigate this issue, existing approaches often rely on externally trained critics or symbolic tools, reducing agent autonomy.
This observation helps explain why the agent achieves near-perfect superficial syntactic alignment yet fails to detect or resolve deeper semantic errors.
This paper presents epistemic blinding in the context of an agentic system that uses large language models to reason across multiple biological datasets for drug target prioritization.
The complete target identification system is described - including LLM-guided evolutionary optimization of scoring functions and blinded agentic reasoning for target rationalization - with demonstration that both stages operate without…
