Tim Rocktäschel

Check Your Work: Structured Checklist Feedback for Improving Large Language Models ACL 2026 BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games ICLR 2025 Investigating Non-Transitivity in LLM-as-a-Judge ICML 2025 Procedural Knowledge in Pretraining Drives Reasoning in Large Language Models ICLR 2025 Debating with More Persuasive LLMs Leads to More Truthful Answers ICML 2024 Genie: Generative Interactive Environments ICML 2024 H-GAP: Humanoid Control with a Generalist Planner ICLR 2024 JaxMARL: Multi-Agent RL Environments and Algorithms in JAX NeurIPS 2024 Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks ICLR 2024 Position: Open-Endedness is Essential for Artificial Superhuman Intelligence ICML 2024 Promptbreeder: Self-Referential Self-Improvement via Prompt Evolution ICML 2024 Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts NeurIPS 2024 Efficient Planning in a Compact Latent Action Space ICLR 2023 Human-Timescale Adaptation in an Open-Ended Task Space ICML 2023 MAESTRO: Open-Ended Environment Design for Multi-Agent Reinforcement Learning ICLR 2023 The Goldilocks of Pragmatic Understanding: Fine-Tuning Strategy Matters for Implicature Resolution by LLMs NeurIPS 2023 Dungeons and Data: A Large-Scale NetHack Dataset NeurIPS 2022 Evolving Curricula with Regret-Based Environment Design ICML 2022 Exploration via Elliptical Episodic Bonuses NeurIPS 2022 GriddlyJS: A Web IDE for Reinforcement Learning NeurIPS 2022 Grounding Aleatoric Uncertainty for Unsupervised Environment Design NeurIPS 2022 Improving Intrinsic Exploration with Language Abstractions NeurIPS 2022 Improving Policy Learning via Language Dynamics Distillation NeurIPS 2022 Learning General World Models in a Handful of Reward-Free Deployments NeurIPS 2022 How to Motivate Your Dragon: Teaching Goal-Driven Agents to Speak and Act in Fantasy Worlds NAACL 2021 KILT: a Benchmark for Knowledge Intensive Language Tasks NAACL 2021 Learning with AMIGo: Adversarially Motivated Intrinsic Goals ICLR 2021 My Body is a Cage: the Role of Morphology in Graph-Based Incompatible Control ICLR 2021 Prioritized Level Replay ICML 2021 Replay-Guided Adversarial Environment Design NeurIPS 2021 Avoiding the Hypothesis-Only Bias in Natural Language Inference via Ensemble Adversarial Training EMNLP 2020 Differentiable Reasoning on Large Knowledge Bases and Natural Language AAAI 2020 Generating Interactive Worlds with Text AAAI 2020 How Decoding Strategies Affect the Verifiability of Generated Text EMNLP 2020 Learning Reasoning Strategies in End-to-End Differentiable Proving ICML 2020 Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks NeurIPS 2020 RIDE: Rewarding Impact-Driven Exploration for Procedurally-Generated Environments ICLR 2020 RTFM: Generalising to New Environment Dynamics via Reading ICLR 2020 The NetHack Learning Environment NeurIPS 2020 A Baseline for Any Order Gradient Estimation in Stochastic Computation Graphs ICML 2019 A Survey of Reinforcement Learning Informed by Natural Language IJCAI 2019 Language Models as Knowledge Bases? EMNLP 2019 Learning to Speak and Act in a Fantasy Text Adventure Game EMNLP 2019 NLProlog: Reasoning with Weak Unification for Question Answering in Natural Language ACL 2019 Stable Opponent Shaping in Differentiable Games ICLR 2019 DiCE: The Infinitely Differentiable Monte Carlo Estimator ICML 2018 e-SNLI: Natural Language Inference with Natural Language Explanations NeurIPS 2018 Interpretation of Natural Language Rules in Conversational Machine Reading EMNLP 2018 Jack the Reader – A Machine Reading Framework ACL 2018 TreeQN and ATreeC: Differentiable Tree-Structured Models for Deep Reinforcement Learning ICLR 2018 End-to-end Differentiable Proving NeurIPS 2017 Programming with a Differentiable Forth Interpreter ICML 2017 Lifted Rule Injection for Relation Embeddings EMNLP 2016 Stance Detection with Bidirectional Conditional Encoding EMNLP 2016 Injecting Logical Background Knowledge into Embeddings for Relation Extraction NAACL 2015 Matrix and Tensor Factorization Methods for Natural Language Processing ACL 2015 WOLFE: An NLP-friendly Declarative Machine Learning Stack NAACL 2015 WBI-DDI: Drug-Drug Interaction Extraction using Majority Voting SemEval 2013 WBI-NER: The impact of domain-specific features on the performance of identifying and classifying mentions of drugs SemEval 2013