paper-with-me

Papers

Predicting Task Difficulty Without Rollouts

2026-08-06 · Stefan Krsteski, Charlotte Meyer arxiv

Task difficulty dictates an agent's likelihood of success, and estimating it without rollouts means forecasting this directly from a task description before executing costly simulations in stateful environments. Reliable estimates would therefore allow environment designers to calibrate evaluation benchmarks and construct progressive training curricula. This becomes increasingly important as agents move into long-horizon domains, where empirical trial-and-error is a severe computational bottleneck. Prior work on early prediction is limited to static tasks or isolated coding environments, often relying on narrow features and inaccurate evaluation metrics. We study \textit{ex ante} difficulty prediction across 17 agentic benchmarks spanning coding, mathematics, machine learning, web navigation, function calling, and other domains. We show that AUC can mask poor difficulty estimates, identify token-level entropy as a useful predictive signal, and show how residuals between expected and observed difficulty can expose hidden environment flaws such as contamination and infeasibility.

📄 PDF Abstract BibTeX arXiv:2608.05797

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

CODA: Difficulty-Aware Compute Allocation for Adaptive Reasoning

2026-03-09 · Siye Wu, Jian Xie, Yikai Zhang, Yanghua Xiao arxiv

The emergence of large reasoning models demonstrates that scaling inference-time compute significantly enhances performance on complex tasks. However, it often falls into another trap: overthinking simple problems, where…

Where Rollouts Begin: Low-Load, High-Leverage First-Token Diversification for RLVR

2026-05-27 · Soeun Kim, Albert No arxiv

Reinforcement Learning with Verifiable Rewards (RLVR) trains reasoning models without labeled trajectories, relying on grouped rollouts to expose the policy to alternative reasoning paths and a verifier to score them. Ro…

Reinforcement Learning

LLM-as-a-Tutor: Policy-Aware Prompt Adaptation for Non-Verifiable RL

2026-07-05 · Yujin Kim, Namgyu Ho, Sangmin Hwang, Joonkee Kim 외 hf

Reinforcement learning (RL) for non-verifiable instruction following increasingly relies on LLM judges with prompt-specific rubrics as reward signals. While recent methods adapt these rubrics to the evolving policy durin…

Reinforcement LearningInstruction Following

Predicting the Relative Difficulty of Single Sentences With and Without Surrounding Context

2016-06-27 · EMNLP 2016 11 · Elliot Schumacher, Maxine Eskenazi, Gwen Frishkoff, Kevyn Collins-Thompson

The problem of accurately predicting relative reading difficulty across a set of sentences arises in a number of important natural language applications, such as finding and curating effective usage examples for intellig…

Improving Data Efficiency for LLM Reinforcement Fine-tuning Through Difficulty-targeted Online Data Selection and Rollout Replay

2025-06-05 · Yifan Sun, Jingyan Shen, Yibin Wang, Tianyu Chen 외

Reinforcement learning (RL) has become an effective approach for fine-tuning large language models (LLMs), particularly to enhance their reasoning capabilities. However, RL fine-tuning remains highly resource-intensive, …

Reinforcement Learning (RL)