RNG-Bench evaluates MLLMs on hidden-observation reconstruction in non-Markov games, finds forgetting as the dominant error source, and shows fine-tuning on optimal rollouts improves performance with transfer to other benchmarks.
hub
Balrog: Bench- marking agentic llm and vlm reasoning on games
19 Pith papers cite this work, alongside 2 external citations. Polarity classification is still indexing.
19
Pith papers citing it
2
external citations · external index
hub tools
citation-role summary
background 3
dataset 1
citation-polarity summary
representative citing papers
RTSGameBench is a new extensible benchmark for VLMs using diverse RTS matchups, diagnostic mini-games targeting individual competencies, and a self-evolving query-to-game generator, with results showing poor VLM performance on tight coordination and large-scale tasks.
AgentBeats implements agentified evaluation of diverse AI agents through standardized interfaces, validated at scale in a five-month competition with 298 judges and 467 subjects plus a coding case study.
VLATIM benchmark reveals large VLMs excel at high-level planning in physics puzzles but struggle with precise visual grounding and mouse control, so they lack human-like problem-solving capabilities.
Agentick is a new benchmark for sequential decision-making agents that evaluates RL, LLM, VLM, hybrid, and human approaches across 37 tasks and finds no single method dominates.
COSPLAY co-evolves an LLM decision agent with a skill bank agent to improve long-horizon game performance, reporting over 25.1% average reward gains versus frontier LLM baselines on single-player benchmarks.
Orak is a foundational benchmark providing training data, interfaces, and evaluation tools for LLM agents across diverse video game genres.
AutoMem automates memory structure revision and proficiency training in LLMs, delivering 2x-4x performance gains on long-horizon games without altering task-action behavior.
OmniGameArena is a unified UE5 benchmark with 12 games and the IDC harness for cold-start scores and improvement dynamics of VLM agents.
DemoEvolve bootstraps harness evolution with demonstrations to achieve more stable and effective edits than self-rollout search in sparse-feedback environments like Balatro.
CAGE uses common-agency games and an EPEC algorithm to compute equilibrium policies that balance multiple conflicting objectives for test-time LLM alignment.
Behavior Cue Reasoning trains LLMs to emit special tokens before behaviors, enabling monitors to cut up to 50% wasted reasoning tokens and recover safe actions from 80% of unsafe traces, more than doubling success rates with no performance cost.
Hierarchical Behaviour Spaces uses linear combinations of reward functions to induce expressive behavior spaces in hierarchical RL, yielding strong performance on NetHack primarily through better exploration rather than long-term planning.
The manuscript body introduces PokeGym, a vision-only automated 3D-game benchmark, while the abstract claims a G-EvoMAC method and 60.18% success rate absent from the body.
This survey categorizes agentic environments for LLMs by eight attributes and domains, introduces symbolic and neural synthesis paradigms with evaluation, and outlines four agent evolution pathways plus three environment evolution paradigms.
A dual-agent closed-loop system integrates Theory of Mind reasoning with multimodal video generation to create social avatars that outperform full-information baselines on dialogue quality under information asymmetry.
AtlasVA organizes VLM agent memory into spatial heatmaps, visual exemplars, and symbolic skills, evolving atlases from trajectories to act as potential-based shaping rewards in teacher-free reinforcement learning.
The paper organizes research on generalist game AI into Dataset, Model, Harness, and Benchmark pillars and charts a five-level progression from single-game mastery to agents that create and live inside game multiverses.
The paper analyzes CPU bottlenecks in agentic AI serving, selects representative workloads, and demonstrates that CPU-aware scheduling optimizations COMB and MAS can reduce P50 latency by up to 1.7x and total latency by up to 2.49x on two hardware systems.
citing papers explorer
-
Beyond the Current Observation: Evaluating Multimodal Large Language Models in Controllable Non-Markov Games
RNG-Bench evaluates MLLMs on hidden-observation reconstruction in non-Markov games, finds forgetting as the dominant error source, and shows fine-tuning on optimal rollouts improves performance with transfer to other benchmarks.
-
RTSGameBench: An RTS Benchmark for Strategic Reasoning by Vision-Language Models
RTSGameBench is a new extensible benchmark for VLMs using diverse RTS matchups, diagnostic mini-games targeting individual competencies, and a self-evolving query-to-game generator, with results showing poor VLM performance on tight coordination and large-scale tasks.
-
AgentBeats: Agentifying Agent Assessment for Openness, Standardization, and Reproducibility
AgentBeats implements agentified evaluation of diverse AI agents through standardized interfaces, validated at scale in a five-month competition with 298 judges and 467 subjects plus a coding case study.
-
Do Vision-Language-Models show human-like logical problem-solving capability in point and click puzzle games?
VLATIM benchmark reveals large VLMs excel at high-level planning in physics puzzles but struggle with precise visual grounding and mouse control, so they lack human-like problem-solving capabilities.
-
Agentick: A Unified Benchmark for General Sequential Decision-Making Agents
Agentick is a new benchmark for sequential decision-making agents that evaluates RL, LLM, VLM, hybrid, and human approaches across 37 tasks and finds no single method dominates.
-
Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Tasks
COSPLAY co-evolves an LLM decision agent with a skill bank agent to improve long-horizon game performance, reporting over 25.1% average reward gains versus frontier LLM baselines on single-player benchmarks.
-
Orak: A Foundational Benchmark for Training and Evaluating LLM Agents on Diverse Video Games
Orak is a foundational benchmark providing training data, interfaces, and evaluation tools for LLM agents across diverse video game genres.
-
AutoMem: Automated Learning of Memory as a Cognitive Skill
AutoMem automates memory structure revision and proficiency training in LLMs, delivering 2x-4x performance gains on long-horizon games without altering task-action behavior.
-
OmniGameArena: A Unified UE5 Benchmark for VLM Game Agents with Improvement Dynamics
OmniGameArena is a unified UE5 benchmark with 12 games and the IDC harness for cold-start scores and improvement dynamics of VLM agents.
-
DemoEvolve: Overcoming Sparse Feedback in Agentic Harness Evolution with Demonstrations
DemoEvolve bootstraps harness evolution with demonstrations to achieve more stable and effective edits than self-rollout search in sparse-feedback environments like Balatro.
-
Common-agency Games for Multi-Objective Test-Time Alignment
CAGE uses common-agency games and an EPEC algorithm to compute equilibrium policies that balance multiple conflicting objectives for test-time LLM alignment.
-
Behavior Cue Reasoning: Monitorable Reasoning Improves Efficiency and Safety through Oversight
Behavior Cue Reasoning trains LLMs to emit special tokens before behaviors, enabling monitors to cut up to 50% wasted reasoning tokens and recover safe actions from 80% of unsafe traces, more than doubling success rates with no performance cost.
-
Hierarchical Behaviour Spaces
Hierarchical Behaviour Spaces uses linear combinations of reward functions to induce expressive behavior spaces in hierarchical RL, yielding strong performance on NetHack primarily through better exploration rather than long-term planning.
-
Mastering PokeGym: Graph-Guided Multimodal Evolution at Test Time
The manuscript body introduces PokeGym, a vision-only automated 3D-game benchmark, while the abstract claims a G-EvoMAC method and 60.18% success rate absent from the body.
-
Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application
This survey categorizes agentic environments for LLMs by eight attributes and domains, introduces symbolic and neural synthesis paradigms with evaluation, and outlines four agent evolution pathways plus three environment evolution paradigms.
-
Resonant Minds: Closed-Loop Social Avatars with Theory of Mind
A dual-agent closed-loop system integrates Theory of Mind reasoning with multimodal video generation to create social avatars that outperform full-information baselines on dialogue quality under information asymmetry.
-
AtlasVA: Self-Evolving Visual Skill Memory for Teacher-Free VLM Agents
AtlasVA organizes VLM agent memory into spatial heatmaps, visual exemplars, and symbolic skills, evolving atlases from trajectories to act as potential-based shaping rewards in teacher-free reinforcement learning.
-
Towards Generalist Game Players: An Investigation of Foundation Models in the Game Multiverse
The paper organizes research on generalist game AI into Dataset, Model, Harness, and Benchmark pillars and charts a five-level progression from single-game mastery to agents that create and live inside game multiverses.
-
Towards Understanding, Analyzing, and Optimizing Agentic AI Execution: A CPU-Centric Perspective
The paper analyzes CPU bottlenecks in agentic AI serving, selects representative workloads, and demonstrates that CPU-aware scheduling optimizations COMB and MAS can reduce P50 latency by up to 1.7x and total latency by up to 2.49x on two hardware systems.