Skip to content

Researcher Tools

Human Feedback and Eval Paper Explorer

A focused feed for RLHF, preference data, rater protocols, agent evaluation, and LLM-as-judge research. Every paper includes structured metadata for quick triage.

Total papers: 387 Search mode: keyword Shortlist (0) RSS

Featured Papers

Popular high-signal papers with direct links to full protocol pages.

Browse by Topic

Jump directly into tag and hub pages to crawl deeper content clusters.

Popular Tags

Top Protocol Hubs

Weekly Eval Paper Digest

The top RLHF, evaluation, and human feedback papers — curated and summarized every Friday.

No spam. Unsubscribe anytime.

Start Here By Objective

Pick your immediate research objective and jump directly to high-signal pages, not generic search.

Scale Your Evaluation Team

Need human evaluators for your benchmark or preference study? OpenTrain sources pre-vetted domain experts into your annotation pipeline.

Match reason: Title directly matches "MATH".

Score: 80% Moderate protocol signal Freshness: Warm Status: Ready
Automatic Metrics Math
  • Recent work has explored the use of large language models (LLMs) to generate tutoring responses in mathematics, yet it remains unclear how closely their instructional behavior aligns with expert human practice.
  • Regression analyses show that pressing for accuracy and reasoning, restating and revoicing, and lexical diversity, are positively associated with perceived pedagogical quality, whereas higher levels of agentic and polite language are…
Open paper
AgentMath: Empowering Mathematical Reasoning for Large Language Models via Tool-Augmented Agent

Haipeng Luo, Huawen Feng, Qingfeng Sun, Can Xu, Kai Zheng, Yufei Wang · Dec 23, 2025

Citations: 0

Match reason: Title directly matches "MATH".

Score: 80% Moderate protocol signal Freshness: Warm Status: Ready
Automatic Metrics MathCoding
  • In this work, we present AgentMath, an agent framework that seamlessly integrates language models' reasoning capabilities with code interpreters' computational precision to efficiently tackle complex mathematical problems.
  • Specifically, AgentMath-30B-A3B attains 90.6%, 86.4%, and 73.8% accuracy respectively, surpassing OpenAI-o3-mini and Claude-Opus-4.0-Thinking while remaining competitive with OpenAI-o3, Gemini-2.5-Pro, and DeepSeek-R1-671B-0528.These…
Open paper
Estimating Text Temperature with Language Models

Nikolay Mikhaylovskiy · Jan 5, 2026

Citations: 0

Match reason: Keyword overlap 1/1 across title and protocol fields.

Score: 77% Sparse protocol signal Freshness: Warm Status: Ready
MathCoding
  • Following it, we propose a procedure to estimate the temperature of any text, including ones written by humans, with respect to a given language model.
Open paper
CogFlow: Bridging Perception and Reasoning through Knowledge Internalization for Visual Mathematical Problem Solving

Shuhang Chen, Yunqiu Xu, Junjie Xie, Aojun Lu, Tao Feng, Zeying Huang · Jan 5, 2026

Citations: 0

Match reason: Title directly matches "MATH".

Score: 73% Sparse protocol signal Freshness: Warm Status: Ready
Math
  • Motivated by this, we present CogFlow, a novel cognitive-inspired three-stage framework that incorporates a knowledge internalization stage, explicitly simulating the hierarchical flow of human reasoning:…
  • Comprehensive experiments and analysis on commonly used visual mathematical reasoning benchmarks validate the superiority of the proposed CogFlow.
Open paper
Intrinsic-Metric Physics-Informed Neural Networks (IM-PINN) for Reaction-Diffusion Dynamics on Complex Riemannian Manifolds

Julian Evan Chrisnanto, Salsabila Rahma Alia, Nurfauzi Fadillah, Yulison Herry Chrisnanto · Dec 26, 2025

Citations: 0

Match reason: Keyword overlap 1/1 across title and protocol fields.

Score: 73% Sparse protocol signal Freshness: Warm Status: Ready
Math
  • Benchmarking against the Surface Finite Element Method (SFEM) reveals superior physical rigor: the IM-PINN achieves global mass conservation error of E_{mass} \approx 0.157 versus SFEM's 0.258, acting as a thermodynamically consistent…
Open paper
Generative Adversarial Reasoner: Enhancing LLM Reasoning with Adversarial Reinforcement Learning

Qihao Liu, Luoxin Ye, Wufei Ma, Yu-Cheng Chou, Alan Yuille · Dec 18, 2025

Citations: 0

Match reason: Keyword overlap 1/1 across title and protocol fields.

Score: 78% Moderate protocol signal Freshness: Cold Status: Ready
Pairwise Preference Automatic Metrics Math
  • Across various mathematical benchmarks, the method delivers consistent gains over strong baselines with standard RL post-training.
  • The modular discriminator also enables flexible reward shaping for objectives such as teacher distillation, preference alignment, and mathematical proof-based reasoning.
Open paper
More Agents Improve Math Problem Solving but Adversarial Robustness Gap Persists

Khashayar Alavi, Zhastay Yeltay, Lucie Flek, Akbar Karimi · Nov 10, 2025

Citations: 0

Match reason: Title directly matches "MATH".

Score: 78% Moderate protocol signal Freshness: Cold Status: Ready
Automatic Metrics Math
  • These perturbations include punctuation noise with three intensities (10%, 30%, 50%), plus real-world and human-like typos (WikiTypo, R2ATA).
  • Using a unified sampling-and-voting framework (Agent Forest), we evaluate six open-source models (Qwen3-4B/14B, Llama3.1-8B, Mistral-7B, Gemma3-4B/12B) across four benchmarks (GSM8K, MATH, MMLU-Math, MultiArith), with various numbers of…
Open paper
Thinking with Video: Video Generation as a Promising Multimodal Reasoning Paradigm

Jingqi Tong, Yurong Mou, Hangcheng Li, Mingzhe Li, Yongzhuo Yang, Ming Zhang · Nov 6, 2025

Citations: 0

Match reason: Keyword overlap 1/1 across title and protocol fields.

Score: 78% Moderate protocol signal Freshness: Cold Status: Ready
Automatic Metrics Math
  • To support this exploration, we developed the Video Thinking Benchmark (VideoThinkBench), which covers both vision-centric tasks (e.g., Eyeballing Puzzles) and text-centric tasks (e.g., GSM8K and MMMU).
  • Our evaluation on VideoThinkBench establishes Sora-2 as a capable reasoner.
Open paper
KV Cache Transform Coding for Compact Storage in LLM Inference

Konrad Staniszewski, Adrian Łańcucki · Nov 3, 2025

Citations: 0

Match reason: Keyword overlap 1/1 across title and protocol fields.

Score: 78% High protocol signal Freshness: Cold Status: Ready
Automatic Metrics MathCoding
  • We test KVTC with Llama 3, Mistral NeMo, and R1-Qwen 2.5 models across benchmarks including AIME25, GSM8K, LiveCodeBench, LongBench, MATH-500, MMLU, Qasper and RULER.
Open paper
Group Representational Position Encoding

Yifan Zhang, Zixiang Chen, Yifeng Liu, Zhen Qin, Huizhuo Yuan, Kangping Xu · Dec 8, 2025

Citations: 0

Match reason: Keyword overlap 1/1 across title and protocol fields.

Score: 75% Moderate protocol signal Freshness: Cold Status: Ready
Automatic Metrics MathLaw
  • Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
Open paper
Citations: 0

Match reason: Keyword overlap 1/1 across title and protocol fields.

Score: 75% Moderate protocol signal Freshness: Cold Status: Ready
Automatic Metrics Math
  • The paper presents the formulation, implementation, and evaluation of the ArcGD optimiser.
  • The evaluation is conducted initially on a non-convex benchmark function and subsequently on a real-world ML dataset.
Open paper
CDLM: Consistency Diffusion Language Models For Faster Sampling

Minseo Kim, Chenfeng Xu, Coleman Hooper, Harman Singh, Ben Athiwaratkun, Ce Zhang · Nov 24, 2025

Citations: 0

Match reason: Keyword overlap 1/1 across title and protocol fields.

Score: 75% Moderate protocol signal Freshness: Cold Status: Ready
Automatic Metrics MathCoding
  • The full training and evaluation code is available at https://github.com/SqueezeAILab/CDLM.
Open paper
Citations: 0

Match reason: Keyword overlap 1/1 across title and protocol fields.

Score: 71% Sparse protocol signal Freshness: Cold Status: Ready
MathCoding
  • We propose a fast automatic prompt construction algorithm that augments human instructions by generating a small set of few shot examples.
  • For faster execution, we use aggressive subsampling and a replay buffer for faster evaluations.
Open paper
When to Think and When to Look: Uncertainty-Guided Lookback

Jing Bi, Filippos Bellos, Junjia Guo, Yayuan Li, Chao Huang, Yolo Y. Tang · Nov 19, 2025

Citations: 0

Match reason: Keyword overlap 1/1 across title and protocol fields.

Score: 71% Sparse protocol signal Freshness: Cold Status: Ready
Math
  • We further show that this decoding strategy generalizes, yielding consistent improvements on five additional benchmarks, including two broad multimodal suites and math focused visual reasoning datasets.
Open paper
Cache What Lasts: Token Retention for Memory-Bounded KV Cache in LLMs

Ngoc Bui, Shubham Sharma, Simran Lamba, Saumitra Mishra, Rex Ying · Dec 3, 2025

Citations: 0

Match reason: Keyword overlap 1/1 across title and protocol fields.

Score: 78% High protocol signal Freshness: Cold Status: Fallback
Automatic Metrics Long Horizon Math
  • Across mathematical reasoning (GSM8K, MATH-500, AIME24), procedural generation (LongProc), conversational long-memory benchmarks (LongMemEval), and long-context understanding (LongBenchV2 and SCBench), TRIM-KV consistently outperforms…
  • Qualitative analyses further reveal that learned retention scores align with human intuition, naturally recovering heuristics such as sink tokens, sliding windows, and gist compression without explicit design.
Open paper
Global Sensitivity Analysis for Engineering Design Based on Individual Conditional Expectations

Pramudita Satria Palar, Paul Saves, Rommel G. Regis, Koji Shimoyama, Shigeru Obayashi, Nicolas Verstaevel · Dec 12, 2025

Citations: 0

Match reason: Keyword overlap 1/1 across title and protocol fields.

Score: 68% Sparse protocol signal Freshness: Cold Status: Ready
Math
  • Comparative evaluations were performed on three cases: a 5-variable analytical function, a 5-variable wind-turbine fatigue problem, and a 9-variable airfoil aerodynamics case, where ICE-based sensitivity was benchmarked against PDP, SHapley…
Open paper
Stronger Normalization-Free Transformers

Mingzhi Chen, Taiming Lu, Jiachen Zhu, Mingjie Sun, Zhuang Liu · Dec 11, 2025

Citations: 0

Match reason: Keyword overlap 1/1 across title and protocol fields.

Score: 68% Sparse protocol signal Freshness: Cold Status: Ready
Math
  • Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
Open paper
Rectifying LLM Thought from Lens of Optimization

Junnan Liu, Hongwei Liu, Songyang Zhang, Kai Chen · Dec 1, 2025

Citations: 0

Match reason: Keyword overlap 1/1 across title and protocol fields.

Score: 68% Sparse protocol signal Freshness: Cold Status: Ready
MathCoding
  • Extensive experiments across multiple reinforcement learning algorithms and diverse LLMs, evaluated on benchmarks spanning mathematics, science, and coding, demonstrate that RePro consistently enhances reasoning performance and mitigates…
Open paper
Long Grounded Thoughts: Synthesizing Visual Problems and Reasoning Chains at Scale

David Acuna, Chao-Han Huck Yang, Yuntian Deng, Jaehun Jung, Ximing Lu, Prithviraj Ammanabrolu · Nov 7, 2025

Citations: 0

Match reason: Keyword overlap 1/1 across title and protocol fields.

Score: 75% Moderate protocol signal Freshness: Cold Status: Fallback
Pairwise Preference Math
  • We introduce a framework able to synthesize vision-centric problems spanning diverse levels of complexity, and the resulting dataset with over 1M high-quality problems including: reasoning traces, preference data, and instruction prompts…
  • Remarkably, finetuning Qwen2.5-VL-7B on our data outperforms existing open-data baselines across evaluated vision-centric benchmarks, and our best configurations match or surpass strong closed-data models such as MiMo-VL-7B-RL on Vstar…
Open paper

Protocol Hubs

Get Started

Join the #1 Platform for AI Training Talent

Where top AI builders and expert AI Trainers connect to build the future of AI.
Self-Service
Post a Job
Post your project and get a shortlist of qualified AI Trainers and Data Labelers. Hire and manage your team in the tools you already use.
Managed Service
For Large Projects
Done-for-You
We recruit, onboard, and manage a dedicated team inside your tools. End-to-end operations for large or complex projects.
For Freelancers
Join as an AI Trainer
Find AI training and data labeling projects across platforms, all in one place. One profile, one application process, more opportunities.