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: 20 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.

QED-Nano: Teaching a Tiny Model to Prove Hard Theorems

LM-Provers, Yuxiao Qu, Amrith Setlur, Jasper Dekoninck, Edward Beeching, Jia Li · Apr 6, 2026

Citations: 0

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

Score: 100% Moderate protocol signal Freshness: Hot Status: Ready
Rubric Rating Automatic Metrics MathCoding
  • To support further research on open mathematical reasoning, we release the full QED-Nano pipeline, including the QED-Nano and QED-Nano-SFT models, the FineProofs-SFT and FineProofs-RL datasets, and the training and evaluation code.
Open paper
Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters

Ailin Huang, Ang Li, Aobo Kong, Bin Wang, Binxing Jiao, Bo Dong · Feb 11, 2026

Citations: 0

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

Score: 100% High protocol signal Freshness: Warm Status: Ready
Pairwise Preference Tool Use MathCoding
  • We introduce Step 3.5 Flash, a sparse Mixture-of-Experts (MoE) model that bridges frontier-level agentic intelligence and computational efficiency.
  • Step 3.5 Flash demonstrates strong performance across agent, coding, and math tasks, achieving 85.4% on IMO-AnswerBench, 86.4% on LiveCodeBench-v6 (2024.08-2025.05), 88.2% on tau2-Bench, 69.0% on BrowseComp (with context management), and…
Open paper

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

Score: 100% Moderate protocol signal Freshness: Warm Status: Ready
Rubric Rating Simulation Env Tool Use Math
  • Small LLMs often struggle to match the agentic capabilities of large, costly models.
  • While reinforcement learning can help, progress has been limited by two structural bottlenecks: existing open-source agentic training data are narrow in task variety and easily solved; real-world APIs lack diversity and are unstable for…
Open paper

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

Score: 100% High protocol signal Freshness: Hot Status: Fallback
Automatic Metrics Long Horizon MathCoding
  • Using roughly 48 execution-verified HumanEval training solutions, tuning a single initial state matrix per recurrent layer, with zero inference overhead, outperforms LoRA by +10.8 pp (p < 0.001) on HumanEval.
  • Cross-domain transfer is significant on MATH-500 (+4.8 pp, p = 0.00002, 8 seeds) and GSM8K (+2.8 pp, p = 0.0003, 10 seeds); a text-to-SQL benchmark (Spider) shows no transfer, consistent with the trajectory-steering mechanism.
Open paper
MAS-ZERO: Designing Multi-Agent Systems with Zero Supervision

Zixuan Ke, Austin Xu, Yifei Ming, Xuan-Phi Nguyen, Ryan Chin, Caiming Xiong · May 21, 2025

Citations: 0

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

Score: 98% High protocol signal Freshness: Cold Status: Ready
Critique Edit Automatic Metrics Multi Agent MathCoding
  • Multi-agent systems (MAS) leveraging the impressive capabilities of Large Language Models (LLMs) hold significant potential for tackling complex tasks.
  • It achieves substantial average accuracy improvements of up to 16.69% on reasoning, 16.66% on coding, and 5.45% on agentic tasks, while maintaining cost efficiency.
Open paper
TRIMS: Trajectory-Ranked Instruction Masked Supervision for Diffusion Language Models

Lingjie Chen, Ruizhong Qiu, Yuyu Fan, Yanjun Zhao, Hanghang Tong · Apr 1, 2026

Citations: 0

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

Score: 100% Moderate protocol signal Freshness: Warm Status: Fallback
Automatic Metrics Long Horizon MathCoding
  • Experiments on LLaDA and Dream across math and coding benchmarks show that TRIMS significantly improves the accuracy-parallelism trade-off over both standard MDLM training and train-free acceleration baselines, while achieving competitive…
Open paper
Agent Q-Mix: Selecting the Right Action for LLM Multi-Agent Systems through Reinforcement Learning

Eric Hanchen Jiang, Levina Li, Rui Sun, Xiao Liang, Yubei Li, Yuchen Wu · Apr 1, 2026

Citations: 0

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

Score: 100% High protocol signal Freshness: Warm Status: Fallback
Automatic Metrics Multi Agent MathLaw
  • In this paper, we propose Agent Q-Mix, a reinforcement learning framework that reformulates topology selection as a cooperative Multi-Agent Reinforcement Learning (MARL) problem.
  • Across seven core benchmarks in coding, reasoning, and mathematics, Agent Q-Mix achieves the highest average accuracy compared to existing methods while demonstrating superior token efficiency and robustness against agent failure.
Open paper
Citations: 0

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

Score: 100% Moderate protocol signal Freshness: Warm Status: Fallback
Automatic Metrics Multi Agent MathCoding
  • As a proof of concept, we present GenDB, an LLM-powered agentic system that generates instance-optimized and customized query execution code tailored to specific data, workloads, and hardware resources.
  • We implemented an early prototype of GenDB that uses Claude Code Agent as the underlying component in the multi-agent system, and we evaluate it on OLAP workloads.
Open paper
Test-Time Scaling with Diffusion Language Models via Reward-Guided Stitching

Roy Miles, Aysim Toker, Andreea-Maria Oncescu, Songcen Xu, Jiankang Deng, Ismail Elezi · Feb 26, 2026

Citations: 0

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

Score: 100% Moderate protocol signal Freshness: Warm Status: Fallback
Automatic Metrics Long Horizon MathCoding
  • This modular pipeline separates exploration (diffusion) from evaluation and solution synthesis, avoiding monolithic unified hybrids while preserving broad search.
  • Across math reasoning benchmarks, we find that step-level recombination is most beneficial on harder problems, and ablations highlight the importance of the final AR solver in converting stitched but imperfect rationales into accurate…
Open paper
Do LLMs and VLMs Share Neurons for Inference? Evidence and Mechanisms of Cross-Modal Transfer

Chenhang Cui, An Zhang, Yuxin Chen, Gelei Deng, Jingnan Zheng, Zhenkai Liang · Feb 22, 2026

Citations: 0

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

Score: 100% Moderate protocol signal Freshness: Warm Status: Fallback
Automatic Metrics Long Horizon MathCoding
  • Across diverse mathematics and perception benchmarks, SNRF consistently enhances LVLM inference performance while preserving perceptual capabilities.
Open paper
Native Reasoning Models: Training Language Models to Reason on Unverifiable Data

Yuanfu Wang, Zhixuan Liu, Xiangtian Li, Chaochao Lu, Chao Yang · Feb 12, 2026

Citations: 0

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

Score: 97% Sparse protocol signal Freshness: Warm Status: Fallback
Demonstrations MathCoding
  • The prevailing paradigm for training large reasoning models--combining Supervised Fine-Tuning (SFT) with Reinforcement Learning with Verifiable Rewards (RLVR)--is fundamentally constrained by its reliance on high-quality, human-annotated…
  • This dependency incurs significant data-collection costs, risks embedding human cognitive biases, and confines the reinforcement learning stage to objectively assessable domains like mathematics and coding, leaving a wide range of…
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: 98% 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
Cost-Effective Communication: An Auction-based Method for Language Agent Interaction

Yijia Fan, Jusheng Zhang, Kaitong Cai, Jing Yang, Chengpei Tang, Jian Wang · Nov 17, 2025

Citations: 0

Match reason: Title directly matches "cost".

Score: 98% High protocol signal Freshness: Cold Status: Fallback
Automatic Metrics Multi Agent MathCoding
  • To address this, we introduce the Dynamic Auction-based Language Agent (DALA), a novel framework that treats communication bandwidth as a scarce and tradable resource.
  • Extensive and comprehensive experiments demonstrate that our economically-driven DALA achieves new state-of-the-art performance across seven challenging reasoning benchmarks, including 84.32% on MMLU and a 91.21% pass@1 rate on HumanEval.
Open paper
Towards Hierarchical Multi-Step Reward Models for Enhanced Reasoning in Large Language Models

Teng Wang, Zhangyi Jiang, Zhenqi He, Shenyang Tong, Wenhan Yang, Yanan Zheng · Mar 16, 2025

Citations: 0

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

Score: 98% High protocol signal Freshness: Cold Status: Fallback
Automatic Metrics Long Horizon MathLaw
  • Empirical results on the PRM800K dataset show that HRM, together with HNC, provides more stable and reliable evaluations than PRM.
  • Furthermore, cross-domain evaluations on the MATH500 and GSM8K datasets demonstrate HRM's strong generalization and robustness across a variety of reasoning tasks.
Open paper
Multi-agent deep reinforcement learning with centralized training and decentralized execution for transportation infrastructure management

M. Saifullah, K. G. Papakonstantinou, A. Bhattacharya, S. M. Stoffels, C. P. Andriotis · Jan 23, 2024

Citations: 0

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

Score: 95% Moderate protocol signal Freshness: Cold Status: Fallback
Simulation Env Multi Agent Math
  • To tackle the high dimensionality of state and action spaces, we propose DDMAC-CTDE, a Deep Decentralized Multi-Agent Actor-Critic (DDMAC) reinforcement learning architecture with Centralized Training and Decentralized Execution (CTDE).
  • To demonstrate the utility of the proposed framework, we also develop a new comprehensive benchmark environment representing an existing transportation network in Virginia, U.S., with heterogeneous pavement and bridge assets undergoing nons
Open paper
Learning to Predict Future-Aligned Research Proposals with Language Models

Heng Wang, Pengcheng Jiang, Jiashuo Sun, Zhiyi Shi, Haofei Yu, Jiawei Han · Mar 28, 2026

Citations: 0

Match reason: Matched by broad semantic/index fallback.

Score: 55% Moderate protocol signal Freshness: Warm Status: Fallback
Human EvalAutomatic Metrics MathCoding
  • Across Llama-3.1 and Qwen2.5 models, future-aligned tuning improves future alignment over unaligned baselines (up to +10.6% overall FAS), and domain-expert human evaluation corroborates improved proposal quality.
  • Finally, we demonstrate practical impact by implementing two model-generated proposals with a code agent, obtaining 4.17% accuracy gain on MATH from a new prompting strategy and consistent improvements for a novel model-merging method.
Open paper
SAHOO: Safeguarded Alignment for High-Order Optimization Objectives in Recursive Self-Improvement

Subramanyam Sahoo, Aman Chadha, Vinija Jain, Divya Chaudhary · Mar 6, 2026

Citations: 0

Match reason: Matched by broad semantic/index fallback.

Score: 52% Sparse protocol signal Freshness: Warm Status: Fallback
Critique Edit MathCoding
  • We introduce SAHOO, a practical framework to monitor and control drift through three safeguards: (i) the Goal Drift Index (GDI), a learned multi-signal detector combining semantic, lexical, structural, and distributional measures; (ii)…
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.