163 citations · 198 across the 9 of their papers we have counts for
11 papers
An Architecture for Long-Horizon Agents: Levels, Ticks and Cascaded Intelligence
Erik Nijkamp, Anurag Koul, Egor Pakhomov +1
Language-model agents are increasingly asked to carry out work spanning days or weeks, such as an operations remediation or a research programme. Such a task outlives any context w…
EvoHarnessBench: Can Your Agents Keep Pace with an Evolving Harness?
Zixuan Ke, Vaidehi Patil, Haizhou Shi +9
Modern LLM-based agents operate through a harness of tools, reusable skills, and specialist agents that shapes what they observe and what they can do. In practice, this harness con…
Privileged Likelihood Is Not Automatically Value: Three Checks for Token Credit in On-Policy Self-Distillation
Xuan-Phi Nguyen, Zeyu Leo Liu, Yang Li +4
On-policy self-distillation aims to improve upon reinforcement learning from verifiable rewards (RLVR) by providing token-level scores derived from privileged information, such as…
Laguna M.1/XS.2 Technical Report
Julien Abadji, Marah Abdin, Connor Adams +93
We present Laguna M.1 and Laguna XS.2, two Mixture-of-Experts foundation models built for long-horizon, agentic coding: M.1 has B total parameters (B activated per tok…
SpecAgent: A Speculative Retrieval and Forecasting Agent for Code Completion
George Ma, Anurag Koul, Qi Chen +6
Large Language Models (LLMs) excel at code-related tasks but often struggle in realistic software repositories, where project-specific APIs and cross-file dependencies are crucial.…
PcLast: Discovering Plannable Continuous Latent States
Anurag Koul, Shivakanth Sujit, Shaoru Chen +11
Goal-conditioned planning benefits from learned low-dimensional representations of rich observations. While compact latent representations typically learned from variational autoen…
Offline Policy Comparison with Confidence: Benchmarks and Baselines
Anurag Koul, Mariano Phielipp, Alan Fern
Decision makers often wish to use offline historical data to compare sequential-action policies at various world states. Importantly, computational tools should produce confidence…
Dream and Search to Control: Latent Space Planning for Continuous Control
Anurag Koul, Varun V. Kumar, Alan Fern +1
Learning and planning with latent space dynamics has been shown to be useful for sample efficiency in model-based reinforcement learning (MBRL) for discrete and continuous control…
Re-understanding Finite-State Representations of Recurrent Policy Networks
Mohamad H. Danesh, Anurag Koul, Alan Fern +1
We introduce an approach for understanding control policies represented as recurrent neural networks. Recent work has approached this problem by transforming such recurrent policy…
Learning Finite State Representations of Recurrent Policy Networks
Anurag Koul, Sam Greydanus, Alan Fern
Recurrent neural networks (RNNs) are an effective representation of control policies for a wide range of reinforcement and imitation learning problems. RNN policies, however, are p…
Visualizing and Understanding Atari Agents
Sam Greydanus, Anurag Koul, Jonathan Dodge +1
While deep reinforcement learning (deep RL) agents are effective at maximizing rewards, it is often unclear what strategies they use to do so. In this paper, we take a step toward…