@annoyingreposter.bsky.social
Double monocular O year
December 26, 2025 at 12:23 PM
Double monocular O year
it's too personal of opinion, too subjective to share
December 26, 2025 at 9:47 AM
it's too personal of opinion, too subjective to share
I think it'd be fine if you paid to someone to refresh the information unless you can approve the updates during the approval process
December 26, 2025 at 5:37 AM
I think it'd be fine if you paid to someone to refresh the information unless you can approve the updates during the approval process
big shoutout to Seth Karten and MindGames Arena for their competitions
concordia as always
concordia as always
December 25, 2025 at 8:07 AM
big shoutout to Seth Karten and MindGames Arena for their competitions
concordia as always
concordia as always
Failures of the year:
1. Reevaluating Policy Gradient Methods for Imperfect-Information Games
2. Inability to record the tutorial "Tutorial on General Evaluation of AI Agents".
No more negativity.
1. Reevaluating Policy Gradient Methods for Imperfect-Information Games
2. Inability to record the tutorial "Tutorial on General Evaluation of AI Agents".
No more negativity.
December 25, 2025 at 8:05 AM
Failures of the year:
1. Reevaluating Policy Gradient Methods for Imperfect-Information Games
2. Inability to record the tutorial "Tutorial on General Evaluation of AI Agents".
No more negativity.
1. Reevaluating Policy Gradient Methods for Imperfect-Information Games
2. Inability to record the tutorial "Tutorial on General Evaluation of AI Agents".
No more negativity.
Paper of the year nominees for me:
1. Multi-Actor Generative Artificial Intelligence as a Game Engine
2. Game of Thoughts: Iterative Reasoning in Game-Theoretic
Domains with Large Language Models
3. Soft Condorcet Optimization for Ranking of General Agents
1. Multi-Actor Generative Artificial Intelligence as a Game Engine
2. Game of Thoughts: Iterative Reasoning in Game-Theoretic
Domains with Large Language Models
3. Soft Condorcet Optimization for Ranking of General Agents
December 25, 2025 at 8:03 AM
Paper of the year nominees for me:
1. Multi-Actor Generative Artificial Intelligence as a Game Engine
2. Game of Thoughts: Iterative Reasoning in Game-Theoretic
Domains with Large Language Models
3. Soft Condorcet Optimization for Ranking of General Agents
1. Multi-Actor Generative Artificial Intelligence as a Game Engine
2. Game of Thoughts: Iterative Reasoning in Game-Theoretic
Domains with Large Language Models
3. Soft Condorcet Optimization for Ranking of General Agents
51. Cross-environment Cooperation Enables Zero-shot Multi-agent Coordination
52. Quantifying the Self-Interest Level of Markov Social Dilemmas
53. Jackpot! Alignment as a Maximal Lottery
54. Wider or Deeper? Scaling LLM Inference-Time
Compute with Adaptive Branching Tree Search
Let's stop here.
52. Quantifying the Self-Interest Level of Markov Social Dilemmas
53. Jackpot! Alignment as a Maximal Lottery
54. Wider or Deeper? Scaling LLM Inference-Time
Compute with Adaptive Branching Tree Search
Let's stop here.
December 25, 2025 at 8:01 AM
51. Cross-environment Cooperation Enables Zero-shot Multi-agent Coordination
52. Quantifying the Self-Interest Level of Markov Social Dilemmas
53. Jackpot! Alignment as a Maximal Lottery
54. Wider or Deeper? Scaling LLM Inference-Time
Compute with Adaptive Branching Tree Search
Let's stop here.
52. Quantifying the Self-Interest Level of Markov Social Dilemmas
53. Jackpot! Alignment as a Maximal Lottery
54. Wider or Deeper? Scaling LLM Inference-Time
Compute with Adaptive Branching Tree Search
Let's stop here.
46. Milnor-Myerson Games and The Principles of Artificial Principal-Agent Problems
47. RE-EVALUATING OPEN-ENDED EVALUATION OF LARGE LANGUAGE MODELS
48. The Decrypto Benchmark for Multi-Agent Reasoning and ToM
49. Robust Autonomy Emerges from Self-Play
50. LLM-MEDIATED GUIDANCE OF MARL SYSTEMS
47. RE-EVALUATING OPEN-ENDED EVALUATION OF LARGE LANGUAGE MODELS
48. The Decrypto Benchmark for Multi-Agent Reasoning and ToM
49. Robust Autonomy Emerges from Self-Play
50. LLM-MEDIATED GUIDANCE OF MARL SYSTEMS
December 25, 2025 at 8:01 AM
46. Milnor-Myerson Games and The Principles of Artificial Principal-Agent Problems
47. RE-EVALUATING OPEN-ENDED EVALUATION OF LARGE LANGUAGE MODELS
48. The Decrypto Benchmark for Multi-Agent Reasoning and ToM
49. Robust Autonomy Emerges from Self-Play
50. LLM-MEDIATED GUIDANCE OF MARL SYSTEMS
47. RE-EVALUATING OPEN-ENDED EVALUATION OF LARGE LANGUAGE MODELS
48. The Decrypto Benchmark for Multi-Agent Reasoning and ToM
49. Robust Autonomy Emerges from Self-Play
50. LLM-MEDIATED GUIDANCE OF MARL SYSTEMS
42. Approximating Nash Equilibria in General-Sum
Games via Meta-Learning
43. DEVIATION RATINGS: A GENERAL, CLONE INVARIANT
RATING METHOD
44. Training Language Models for Social Deduction with Multi-Agent Reinforcement Learning
45. EXPECTED RETURN SYMMETRIES
Games via Meta-Learning
43. DEVIATION RATINGS: A GENERAL, CLONE INVARIANT
RATING METHOD
44. Training Language Models for Social Deduction with Multi-Agent Reinforcement Learning
45. EXPECTED RETURN SYMMETRIES
December 25, 2025 at 8:01 AM
42. Approximating Nash Equilibria in General-Sum
Games via Meta-Learning
43. DEVIATION RATINGS: A GENERAL, CLONE INVARIANT
RATING METHOD
44. Training Language Models for Social Deduction with Multi-Agent Reinforcement Learning
45. EXPECTED RETURN SYMMETRIES
Games via Meta-Learning
43. DEVIATION RATINGS: A GENERAL, CLONE INVARIANT
RATING METHOD
44. Training Language Models for Social Deduction with Multi-Agent Reinforcement Learning
45. EXPECTED RETURN SYMMETRIES
39. SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning
40. Deep mechanism design: Learning social and economic
policies for human benefit
41. Meta-Learning in Self-Play Regret Minimization
40. Deep mechanism design: Learning social and economic
policies for human benefit
41. Meta-Learning in Self-Play Regret Minimization
December 25, 2025 at 8:01 AM
39. SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning
40. Deep mechanism design: Learning social and economic
policies for human benefit
41. Meta-Learning in Self-Play Regret Minimization
40. Deep mechanism design: Learning social and economic
policies for human benefit
41. Meta-Learning in Self-Play Regret Minimization
36. Convergent Q-Learning for Infinite-Horizon General-Sum Markov Games through Behavioral Economics
37. Remembering the Markov Property in Cooperative
MARL
38. Constrained Exploitability Descent: An Offline Reinforcement Learning Method for Finding Mixed-Strategy Nash Equilibrium
37. Remembering the Markov Property in Cooperative
MARL
38. Constrained Exploitability Descent: An Offline Reinforcement Learning Method for Finding Mixed-Strategy Nash Equilibrium
December 25, 2025 at 8:01 AM
36. Convergent Q-Learning for Infinite-Horizon General-Sum Markov Games through Behavioral Economics
37. Remembering the Markov Property in Cooperative
MARL
38. Constrained Exploitability Descent: An Offline Reinforcement Learning Method for Finding Mixed-Strategy Nash Equilibrium
37. Remembering the Markov Property in Cooperative
MARL
38. Constrained Exploitability Descent: An Offline Reinforcement Learning Method for Finding Mixed-Strategy Nash Equilibrium
32. Modeling human reputation-seeking behavior in a spatio-temporally complex public good provision game
33. Improving Transformer World Models for Data-Efficient RL
34. MASTER: A Multi-Agent System with LLM Specialized MCTS
35. The Y¯ okai Learning Environment: Tracking Beliefs Over Space and Time
33. Improving Transformer World Models for Data-Efficient RL
34. MASTER: A Multi-Agent System with LLM Specialized MCTS
35. The Y¯ okai Learning Environment: Tracking Beliefs Over Space and Time
December 25, 2025 at 8:01 AM
32. Modeling human reputation-seeking behavior in a spatio-temporally complex public good provision game
33. Improving Transformer World Models for Data-Efficient RL
34. MASTER: A Multi-Agent System with LLM Specialized MCTS
35. The Y¯ okai Learning Environment: Tracking Beliefs Over Space and Time
33. Improving Transformer World Models for Data-Efficient RL
34. MASTER: A Multi-Agent System with LLM Specialized MCTS
35. The Y¯ okai Learning Environment: Tracking Beliefs Over Space and Time
28. Multi-agent cooperation through learning-aware policy gradient
29. Evolution of Societies via Reinforcement Learning
30. ADIOS: Antibody Development via Opponent Shaping
31. Bootstrapping Task Spaces for Self-Improvement
29. Evolution of Societies via Reinforcement Learning
30. ADIOS: Antibody Development via Opponent Shaping
31. Bootstrapping Task Spaces for Self-Improvement
December 25, 2025 at 8:01 AM
28. Multi-agent cooperation through learning-aware policy gradient
29. Evolution of Societies via Reinforcement Learning
30. ADIOS: Antibody Development via Opponent Shaping
31. Bootstrapping Task Spaces for Self-Improvement
29. Evolution of Societies via Reinforcement Learning
30. ADIOS: Antibody Development via Opponent Shaping
31. Bootstrapping Task Spaces for Self-Improvement
24. Smart Cellular Bricks for Decentralized Shape Classification and Damage Recovery
25. CODE WORLD MODELS FOR GENERAL GAME PLAYING
26. EVOLUTION STRATEGIES AT SCALE: LLM FINETUNING BEYOND REINFORCEMENT LEARNING
27. Modeling Others’ Minds as Code
25. CODE WORLD MODELS FOR GENERAL GAME PLAYING
26. EVOLUTION STRATEGIES AT SCALE: LLM FINETUNING BEYOND REINFORCEMENT LEARNING
27. Modeling Others’ Minds as Code
December 25, 2025 at 8:01 AM
24. Smart Cellular Bricks for Decentralized Shape Classification and Damage Recovery
25. CODE WORLD MODELS FOR GENERAL GAME PLAYING
26. EVOLUTION STRATEGIES AT SCALE: LLM FINETUNING BEYOND REINFORCEMENT LEARNING
27. Modeling Others’ Minds as Code
25. CODE WORLD MODELS FOR GENERAL GAME PLAYING
26. EVOLUTION STRATEGIES AT SCALE: LLM FINETUNING BEYOND REINFORCEMENT LEARNING
27. Modeling Others’ Minds as Code
21. Online Decision-Making in Tree-Like Multi-Agent Games with
Transfers
22. NASH POLICY GRADIENT: A POLICY GRADIENT METHOD
WITH ITERATIVELY REFINED REGULARIZATION FOR FINDING
NASH EQUILIBRIA
23. OPPONENT SHAPING IN LLM AGENTS
Transfers
22. NASH POLICY GRADIENT: A POLICY GRADIENT METHOD
WITH ITERATIVELY REFINED REGULARIZATION FOR FINDING
NASH EQUILIBRIA
23. OPPONENT SHAPING IN LLM AGENTS
December 25, 2025 at 8:01 AM
21. Online Decision-Making in Tree-Like Multi-Agent Games with
Transfers
22. NASH POLICY GRADIENT: A POLICY GRADIENT METHOD
WITH ITERATIVELY REFINED REGULARIZATION FOR FINDING
NASH EQUILIBRIA
23. OPPONENT SHAPING IN LLM AGENTS
Transfers
22. NASH POLICY GRADIENT: A POLICY GRADIENT METHOD
WITH ITERATIVELY REFINED REGULARIZATION FOR FINDING
NASH EQUILIBRIA
23. OPPONENT SHAPING IN LLM AGENTS
18. Learning Global Nash Equilibrium in Team Competitive
Games with Generalized Fictitious Cross-Play
19. SPICE : Self-Play In Corpus Environments
Improves Reasoning
20. Aligning Individual and Collective Objectives in Multi-Agent Cooperation
Games with Generalized Fictitious Cross-Play
19. SPICE : Self-Play In Corpus Environments
Improves Reasoning
20. Aligning Individual and Collective Objectives in Multi-Agent Cooperation
December 25, 2025 at 8:01 AM
18. Learning Global Nash Equilibrium in Team Competitive
Games with Generalized Fictitious Cross-Play
19. SPICE : Self-Play In Corpus Environments
Improves Reasoning
20. Aligning Individual and Collective Objectives in Multi-Agent Cooperation
Games with Generalized Fictitious Cross-Play
19. SPICE : Self-Play In Corpus Environments
Improves Reasoning
20. Aligning Individual and Collective Objectives in Multi-Agent Cooperation
15. Estimating cognitive biases with
attention-aware inverse planning
16. A Variational Approach to Mutual Information-Based
Coordination for Multi-Agent Reinforcement Learning
17. Monte Carlo Tree Diffusion for System 2 Planning
attention-aware inverse planning
16. A Variational Approach to Mutual Information-Based
Coordination for Multi-Agent Reinforcement Learning
17. Monte Carlo Tree Diffusion for System 2 Planning
December 25, 2025 at 8:01 AM
15. Estimating cognitive biases with
attention-aware inverse planning
16. A Variational Approach to Mutual Information-Based
Coordination for Multi-Agent Reinforcement Learning
17. Monte Carlo Tree Diffusion for System 2 Planning
attention-aware inverse planning
16. A Variational Approach to Mutual Information-Based
Coordination for Multi-Agent Reinforcement Learning
17. Monte Carlo Tree Diffusion for System 2 Planning
11. HyperMARL: Adaptive Hypernetworks for
Multi-Agent RL
12. Hypernetworks That Evolve Themselves
13. Partner Modelling Emerges in Recurrent Agents
(But Only When It Matters)
14. Robust and Diverse Multi-Agent Learning via
Rational Policy Gradient
Multi-Agent RL
12. Hypernetworks That Evolve Themselves
13. Partner Modelling Emerges in Recurrent Agents
(But Only When It Matters)
14. Robust and Diverse Multi-Agent Learning via
Rational Policy Gradient
December 25, 2025 at 8:01 AM
11. HyperMARL: Adaptive Hypernetworks for
Multi-Agent RL
12. Hypernetworks That Evolve Themselves
13. Partner Modelling Emerges in Recurrent Agents
(But Only When It Matters)
14. Robust and Diverse Multi-Agent Learning via
Rational Policy Gradient
Multi-Agent RL
12. Hypernetworks That Evolve Themselves
13. Partner Modelling Emerges in Recurrent Agents
(But Only When It Matters)
14. Robust and Diverse Multi-Agent Learning via
Rational Policy Gradient
8. Embedded Universal Predictive Intelligence: a
coherent framework for multi-agent learning
9. Social World Model-Augmented Mechanism Design
Policy Learning
10. Evaluating Cooperation with Novel Partners in Unknown En
vironments Using Unsupervised Environment Design
coherent framework for multi-agent learning
9. Social World Model-Augmented Mechanism Design
Policy Learning
10. Evaluating Cooperation with Novel Partners in Unknown En
vironments Using Unsupervised Environment Design
December 25, 2025 at 8:01 AM
8. Embedded Universal Predictive Intelligence: a
coherent framework for multi-agent learning
9. Social World Model-Augmented Mechanism Design
Policy Learning
10. Evaluating Cooperation with Novel Partners in Unknown En
vironments Using Unsupervised Environment Design
coherent framework for multi-agent learning
9. Social World Model-Augmented Mechanism Design
Policy Learning
10. Evaluating Cooperation with Novel Partners in Unknown En
vironments Using Unsupervised Environment Design
4. Neural Mean-Field Games: Extending Mean-Field Game Theory with Neural Stochastic
Differential Equations
5. An Efficient End-to-End Training Approach for
Zero-Shot Human-AI Coordination
6. Terra Nova: A Comprehensive Challenge Environment for
Intelligent Agents
7. Imagined Autocurricula
Differential Equations
5. An Efficient End-to-End Training Approach for
Zero-Shot Human-AI Coordination
6. Terra Nova: A Comprehensive Challenge Environment for
Intelligent Agents
7. Imagined Autocurricula
December 25, 2025 at 8:01 AM
4. Neural Mean-Field Games: Extending Mean-Field Game Theory with Neural Stochastic
Differential Equations
5. An Efficient End-to-End Training Approach for
Zero-Shot Human-AI Coordination
6. Terra Nova: A Comprehensive Challenge Environment for
Intelligent Agents
7. Imagined Autocurricula
Differential Equations
5. An Efficient End-to-End Training Approach for
Zero-Shot Human-AI Coordination
6. Terra Nova: A Comprehensive Challenge Environment for
Intelligent Agents
7. Imagined Autocurricula
Highlights (no specific order):
1. Adaptively Coordinating with Novel Partners via
Learned Latent Strategies
2. Generative Emergent Communication:
Large Language Model is a Collective World Model
3. Superhuman AI for Stratego Using Self-Play
Reinforcement Learning and Test-Time Search
1. Adaptively Coordinating with Novel Partners via
Learned Latent Strategies
2. Generative Emergent Communication:
Large Language Model is a Collective World Model
3. Superhuman AI for Stratego Using Self-Play
Reinforcement Learning and Test-Time Search
December 25, 2025 at 8:01 AM
Highlights (no specific order):
1. Adaptively Coordinating with Novel Partners via
Learned Latent Strategies
2. Generative Emergent Communication:
Large Language Model is a Collective World Model
3. Superhuman AI for Stratego Using Self-Play
Reinforcement Learning and Test-Time Search
1. Adaptively Coordinating with Novel Partners via
Learned Latent Strategies
2. Generative Emergent Communication:
Large Language Model is a Collective World Model
3. Superhuman AI for Stratego Using Self-Play
Reinforcement Learning and Test-Time Search
MERRY CHRISTMASSSSSSSSS
December 25, 2025 at 7:10 AM
MERRY CHRISTMASSSSSSSSS
amazing piece of art
December 25, 2025 at 6:18 AM
amazing piece of art