12 citations · 111 across the 56 of their papers we have counts for
61 papers
Rethinking the Evaluation of Harness Evolution for Agents
Yike Wang, Huaisheng Zhu, Zhengyu Hu +8
Harness evolution is an iterative search procedure that repeatedly evaluates and revises candidate harnesses used for LLM agents using task feedback. We revisit the evaluation of s…
Cracks in the Foundation: Seemingly Minor Architectural Choices Impact Long Context Extension
Amanda Bertsch, Luca Soldaini, Matthew R. Gormley +4
One might imagine that architectural variations within the dense transformer paradigm have a limited effect on accuracy. However, we demonstrate that this is not the case in the lo…
Pretraining Data Can Be Poisoned through Computational Propaganda
Victoria Graf, Hannaneh Hajishirzi, Noah A. Smith +2
Poisoning pretraining data can introduce harmful behaviors to LMs that are difficult to detect and mitigate. Prior work on poisoning pretraining data has largely exploited establis…
Tmax: A simple recipe for terminal agents
Hamish Ivison, Junjie Oscar Yin, Rulin Shao +3
Terminal-using agents have quickly become a popular and important downstream application of language models (LMs). Despite their prevalence, relatively little academic work has exa…
Scaling Test-Time Compute for Agentic Coding
Joongwon Kim, Wannan Yang, Kelvin Niu +13
Test-time scaling has become a powerful way to improve large language models. However, existing methods are best suited to short, bounded outputs that can be directly compared, ran…
Olmo Hybrid: From Theory to Practice and Back
William Merrill, Yanhong Li, Tyler Romero +19
Recent work has demonstrated the potential of non-transformer language models, especially linear recurrent neural networks (RNNs) and hybrid models that mix recurrence and attentio…
Meta-Reinforcement Learning with Self-Reflection for Agentic Search
Teng Xiao, Yige Yuan, Hamish Ivison +6
This paper introduces MR-Search, an in-context meta reinforcement learning (RL) formulation for agentic search with self-reflection. Instead of optimizing a policy within a single…
TurnWise: The Gap between Single- and Multi-turn Language Model Capabilities
Victoria Graf, Valentina Pyatkin, Nouha Dziri +2
Multi-turn conversations are a common and critical mode of language model interaction. However, current open training and evaluation data focus on single-turn settings, failing to…
Learning to Detect Language Model Training Data via Active Reconstruction
Junjie Oscar Yin, John X. Morris, Vitaly Shmatikov +2
Detecting LLM training data is generally framed as a membership inference attack (MIA) problem. However, conventional MIAs operate passively on fixed model weights, using log-likel…
Olmix: A Framework for Data Mixing Throughout LM Development
Mayee F. Chen, Tyler Murray, David Heineman +5
Data mixing -- determining the ratios of data from different domains -- is a first-order concern for training language models (LMs). While existing mixing methods show promise, the…
Small Reward Models via Backward Inference
Yike Wang, Faeze Brahman, Shangbin Feng +3
Reward models (RMs) play a central role throughout the language model (LM) pipeline, particularly in non-verifiable domains. However, the dominant LLM-as-a-Judge paradigm relies on…
DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research
Rulin Shao, Akari Asai, Shannon Zejiang Shen +18
Deep research agents perform multi-step research to produce long-form, well-attributed answers. However, most open deep research agents are trained on easily verifiable short-form…
RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments
Zhiyuan Zeng, Hamish Ivison, Yiping Wang +14
We introduce Reinforcement Learning (RL) with Adaptive Verifiable Environments (RLVE), an approach using verifiable environments that procedurally generate problems and provide alg…
Train for Truth, Keep the Skills: Binary Retrieval-Augmented Reward Mitigates Hallucinations
Tong Chen, Akari Asai, Luke Zettlemoyer +2
Language models often generate factually incorrect information unsupported by their training data, a phenomenon known as extrinsic hallucination. Existing mitigation approaches oft…
RL Grokking Recipe: How Does RL Unlock and Transfer New Algorithms in LLMs?
Yiyou Sun, Yuhan Cao, Pohao Huang +4
It remains an open question whether LLMs can acquire or generalize genuinely new reasoning strategies, beyond the sharpened skills encoded in their parameters during pre-training o…
Fluid Language Model Benchmarking
Valentin Hofmann, David Heineman, Ian Magnusson +7
Language model (LM) benchmarking faces several challenges: comprehensive evaluations are costly, benchmarks often fail to measure the intended capabilities, and evaluation quality…
FlexOlmo: Open Language Models for Flexible Data Use
Weijia Shi, Akshita Bhagia, Kevin Farhat +20
We introduce FlexOlmo, a new class of language models (LMs) that supports (1) distributed training without data sharing, where different model parameters are independently trained…
Signal and Noise: A Framework for Reducing Uncertainty in Language Model Evaluation
David Heineman, Valentin Hofmann, Ian Magnusson +5
Developing large language models is expensive and involves making decisions with small experiments, typically by evaluating on large, multi-task evaluation suites. In this work, we…
RTTC: Reward-Guided Collaborative Test-Time Compute
J. Pablo Muñoz, Jinjie Yuan
Test-Time Compute (TTC) has emerged as a powerful paradigm for enhancing the performance of Large Language Models (LLMs) at inference, leveraging strategies such as Test-Time Train…
Generalizing Verifiable Instruction Following
Valentina Pyatkin, Saumya Malik, Victoria Graf +5
A crucial factor for successful human and AI interaction is the ability of language models or chatbots to follow human instructions precisely. A common feature of instructions are…
SciArena: An Open Evaluation Platform for Non-Verifiable Scientific Literature-Grounded Tasks
Yilun Zhao, Kaiyan Zhang, Tiansheng Hu +15
We present SciArena, an open and collaborative platform for evaluating foundation models on scientific literature-grounded tasks. Unlike traditional benchmarks for scientific liter…
ASTRO: Teaching Language Models to Reason by Reflecting and Backtracking In-Context
Joongwon Kim, Anirudh Goyal, Liang Tan +3
We introduce ASTRO, the "Autoregressive Search-Taught Reasoner", a framework for training language models to reason like search algorithms, explicitly leveraging self-reflection, b…
OMEGA: Can LLMs Reason Outside the Box in Math? Evaluating Exploratory, Compositional, and Transformative Generalization
Yiyou Sun, Shawn Hu, Georgia Zhou +4
Recent large-scale language models (LLMs) with long Chain-of-Thought reasoning-such as DeepSeek-R1-have achieved impressive results on Olympiad-level mathematics benchmarks. Howeve…
RewardBench 2: Advancing Reward Model Evaluation
Saumya Malik, Valentina Pyatkin, Sander Land +4
Reward models are used throughout the post-training of language models to capture nuanced signals from preference data and provide a training target for optimization across instruc…