Skip to content
OpenTrain AIFor AI Companies
← Back to explorer

Tag: Demonstrations

Demonstrations papers in the current HFEPX explorer (108 papers).

Papers in tag: 108

Global RSS

Running a Demonstrations study?

Post a Job →

Research Utility Snapshot

Evaluation Modes

  • Automatic Metrics (5)
  • Simulation Env (1)

Human Feedback Types

  • Demonstrations (20)

Required Expertise

  • General (12)
  • Coding (7)
  • Math (3)
IA2: Alignment with ICL Activations Improves Supervised Fine-Tuning

Aayush Mishra, Daniel Khashabi, Anqi Liu · Sep 26, 2025 · Citations: 0

Demonstrations Automatic Metrics General
  • Performing IA2 as a priming step before SFT significantly improves the accuracy and calibration of model outputs, as shown by our extensive empirical results on 12 popular benchmarks and two model families.
CausalARC: Abstract Reasoning with Causal World Models

Jacqueline Maasch, John Kalantari, Kia Khezeli · Sep 3, 2025 · Citations: 0

Demonstrations Math
  • As a proof-of-concept, we illustrate the use of CausalARC for four language model evaluation settings: (1) abstract reasoning with test-time training, (2) counterfactual reasoning with in-context learning, (3) program synthesis, and (4)…
LaTeXTrans: Structured LaTeX Translation with Multi-Agent Coordination

Ziming Zhu, Chenglong Wang, Haosong Xv, Shunjie Xing, Yifu Huo, Fengning Tian · Aug 26, 2025 · Citations: 0

Demonstrations Automatic Metrics MathCoding
  • In this paper, we introduce LaTeXTrans, a collaborative multi-agent system designed to address this challenge.
  • LaTeXTrans ensures format preservation, structural fidelity, and terminology consistency through six specialized agents: 1) a Parser that decomposes LaTeX into translation-friendly units via placeholder substitution and syntax filtering; 2)…
AmbiSQL: Interactive Ambiguity Detection and Resolution for Text-to-SQL

Zhongjun Ding, Yin Lin, Tianjing Zeng, Rong Zhu, Bolin Ding, Jingren Zhou · Aug 21, 2025 · Citations: 0

Demonstrations General
  • We provide 40 ambiguous queries collected from two real-world benchmarks that SIGMOD'26 attendees can use to explore how disambiguation improves SQL generation quality.
Post-training for Efficient Communication via Convention Formation

Yilun Hua, Evan Wang, Yoav Artzi · Aug 8, 2025 · Citations: 0

Demonstrations General
  • Humans communicate with increasing efficiency in multi-turn interactions, by adapting their language and forming ad-hoc conventions.
  • We evaluate with two new benchmarks focused on this capability.
Programming by Backprop: An Instruction is Worth 100 Examples When Finetuning LLMs

Jonathan Cook, Silvia Sapora, Arash Ahmadian, Akbir Khan, Tim Rocktaschel, Jakob Foerster · Jun 23, 2025 · Citations: 0

Demonstrations Coding
  • Though execution of instructions in training data remains less reliable than when instructions are given in-context, our results demonstrate that procedural knowledge can be noisily `programmed' into LLMs through PBB, with important…
MOBODY: Model Based Off-Dynamics Offline Reinforcement Learning

Yihong Guo, Yu Yang, Pan Xu, Anqi Liu · Jun 10, 2025 · Citations: 0

Demonstrations General
  • We evaluate MOBODY on a wide range of MuJoCo and Adroit benchmarks, demonstrating that it outperforms state-of-the-art off-dynamics RL baselines as well as policy learning methods based on different dynamics learning baselines, with…
Incentivizing Strong Reasoning from Weak Supervision

Yige Yuan, Teng Xiao, Shuchang Tao, Xue Wang, Jinyang Gao, Bolin Ding · May 26, 2025 · Citations: 0

Demonstrations Automatic Metrics Coding
  • Experiments across diverse benchmarks and model architectures demonstrate that weak reasoners can effectively incentivize reasoning in stronger student models, consistently improving performance across a wide range of reasoning tasks.
Training with Pseudo-Code for Instruction Following

Prince Kumar, Rudra Murthy, Riyaz Bhat, Danish Contractor · May 23, 2025 · Citations: 0

Demonstrations MathCoding
  • We evaluate our method on 12 publicly available benchmarks spanning instruction-following, mathematical reasoning, and commonsense reasoning, across six base models.
  • Our results show that models trained with pseudo-code follow instructions more reliably, achieving relative gains of 8-21\% on instruction following benchmarks, while largely preserving and in some cases improving performance on…
REFLEX: Metacognitive Reasoning for Reflective Zero-Shot Robotic Planning with Large Language Models

Wenjie Lin, Jin Wei-Kocsis, Jiansong Zhang, Byung-Cheol Min, Dongming Gan, Paul Asunda · May 20, 2025 · Citations: 0

Demonstrations General
  • Inspired by human metacognitive learning and creative problem-solving, we address this limitation by exploring a fundamental question: Can LLMs be empowered with metacognitive capabilities to reason, reflect, and create, thereby enhancing…
  • We propose a more challenging robotic benchmark task and evaluate our framework on the existing benchmark and the novel task.
Efficient Agent Training for Computer Use

Yanheng He, Jiahe Jin, Pengfei Liu · May 20, 2025 · Citations: 0

Demonstrations Coding
  • We introduce PC Agent-E, an efficient agent training framework that significantly reduces reliance on large-scale human demonstrations.
  • Trained on these enriched trajectories, our PC Agent-E model achieved a remarkable 141 relative improvement, and even surpassed the Claude 3.7 Sonnet by 10% in relative terms on WindowsAgentArena-V2, an improved benchmark we also released.
Structured Agent Distillation for Large Language Model

Jun Liu, Zhenglun Kong, Peiyan Dong, Changdi Yang, Tianqi Li, Hao Tang · May 20, 2025 · Citations: 0

Demonstrations Simulation Env General
  • Large language models (LLMs) exhibit strong capabilities as decision-making agents by interleaving reasoning and actions, as seen in ReAct-style frameworks.
  • We propose Structured Agent Distillation, a framework that compresses large LLM-based agents into smaller student models while preserving both reasoning fidelity and action consistency.