Towards Improving Sequential Decision-Making in LLM Agents via Experience Memory

• URL: http://arxiv.org/abs/2608.03420v1
• Date: Tue, 04 Aug 2026 10:12:12 GMT
• Title: Towards Improving Sequential Decision-Making in LLM Agents via Experience Memory
• Abstract summary: Large language models have improved substantially on single-shot reasoning tasks, but their performance in sequential decision-making is less well understood.<n>We study this on fully-observable two-player zero-sum games, which provide ground-truth evaluation.<n>We show that post-game reflection and rule extraction yield measurable improvements on tic-tac-toe without modifying the model weights.
• Score: 3.4935179780034242
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models have improved substantially on single-shot reasoning tasks, but their performance in sequential decision-making is less well understood. We study this on fully-observable two-player zero-sum games, which provide ground-truth evaluation: outcomes are determined by the rules, and optimality of individual moves can be computed or approximated, without relying on a judge model. Across model tiers, LLMs play suboptimally in simple games such as tic-tac-toe or Connect Four, and lose to MCTS opponents. Obfuscations that preserve the game tree but rewrite its surface form leave performance largely unchanged, indicating the gap is not fully explained by recall of memorized strategies. Motivated by this performance gap, we introduce an agentic framework enhanced with an experience memory designed for the sequential setting and addressing common challenges of sequential decision-making such as credit assignment. We show that post-game reflection and rule extraction yield measurable improvements on tic-tac-toe without modifying the model weights.

Related papers

• Strategy, Not Payoffs: A Behavioural Embedding of Normal-Form Games [8.99869329367482]
  We investigate whether game embeddings can explain and predict changes in LLM strategic capabilities following fine-tuning across different games.<n>We show that while existing structural embeddings memorize game identities and fail to generalize, our behavioural embedding reliably predicts performance changes on held-out games.
  arXiv  Detail & Related papers  (2026-07-30T00:10:21Z)
• Spatial Reasoning in LLM Game Agents: Impact of Causal Context and Multi-Step Planning [56.67877550139192]
  We conduct experiments across varying model scales, reasoning modes, and planning horizons.<n>We introduce a focused GVGAI benchmark consisting of three custom games with five difficulty levels to isolate spatial navigation.<n>Our results show that while larger models with an enabled thinking mode identify their positions more accurately, overall performance in coordinate matching remains limited for smaller models.
  arXiv  Detail & Related papers  (2026-07-22T12:10:45Z)
• Beyond the Current Observation: Evaluating Multimodal Large Language Models in Controllable Non-Markov Games [69.57330692969543]
  We introduce RNG-Bench, a benchmark suite designed to isolate a base model's ability to reconstruct past observations.<n>RNG-Bench includes two complementary games: Matching Pairs, where card identities briefly revealed at specific locations must later be recalled, and 3D Maze, where egocentric views must be integrated into a spatial map.<n>The hardest configurations require contexts of roughly 128K tokens and 350 image inputs per episode, and remain far from saturated by frontier MLLMs.
  arXiv  Detail & Related papers  (2026-06-17T17:59:34Z)
• Reasoning Resides in Layers: Restoring Temporal Reasoning in Video-Language Models with Layer-Selective Merging [62.24239343184817]
  Multimodal adaptation equips large language models with perceptual capabilities, but often weakens the reasoning ability inherited from language-only pretraining.<n>We propose MERIT, a training-free, task-driven model merging framework for restoring temporal reasoning in video-language models.
  arXiv  Detail & Related papers  (2026-04-13T12:41:50Z)
• Your Self-Play Algorithm is Secretly an Adversarial Imitator: Understanding LLM Self-Play through the Lens of Imitation Learning [29.069448000317035]
  We propose a new self-play imitation finetuning algorithm based on the $2$-divergence variational objective with bounded rewards and improved stability.<n> Experiments on various of language model finetuning tasks demonstrate consistent improvements over existing self-play methods.
  arXiv  Detail & Related papers  (2026-02-01T17:50:59Z)
• How Far Are LLMs from Professional Poker Players? Revisiting Game-Theoretic Reasoning with Agentic Tool Use [52.394999779049606]
  Large Language Models (LLMs) are increasingly applied in high-stakes domains.<n>LLMs fail to compete against traditional algorithms.<n>We propose ToolPoker, a tool-integrated reasoning framework.
  arXiv  Detail & Related papers  (2026-01-31T05:45:25Z)
• LLM CHESS: Benchmarking Reasoning and Instruction-Following in LLMs through Chess [30.797553771114746]
  We introduce LLM CHESS, an evaluation framework designed to probe the generalization of reasoning and instruction-following abilities in large language models (LLMs)<n>We rank over 50 open and closed source models by playing against a random opponent using a range of behavioral metrics, including move quality, move legality, hallucinated actions, and game duration.<n>For a subset of top reasoning models, we derive an Elo estimate by playing against a chess engine with variably configured skill, which allows for comparisons between models in an easily understandable way.
  arXiv  Detail & Related papers  (2025-12-01T18:51:08Z)
• GAMEBoT: Transparent Assessment of LLM Reasoning in Games [54.49589494014147]
  GAMEBoT is a gaming arena designed for rigorous assessment of Large Language Models.<n>We benchmark 17 prominent LLMs across eight games, encompassing various strategic abilities and game characteristics.<n>Our results suggest that GAMEBoT presents a significant challenge, even when LLMs are provided with detailed CoT prompts.
  arXiv  Detail & Related papers  (2024-12-18T08:32:53Z)
• Auto-Encoding Bayesian Inverse Games [36.06617326128679]
  We consider the inverse game problem, in which some properties of the game are unknown a priori. Existing maximum likelihood estimation approaches to solve inverse games provide only point estimates of unknown parameters. We take a Bayesian perspective and construct posterior distributions of game parameters. This structured VAE can be trained from an unlabeled dataset of observed interactions.
  arXiv  Detail & Related papers  (2024-02-14T02:17:37Z)
• On the Self-Verification Limitations of Large Language Models on Reasoning and Planning Tasks [17.329365493094542]
  We present a principled empirical study of the performance of GPT-4 in three domains: Game of 24, Graph Coloring, and STRIPS planning. We observe significant performance collapse with self-critique and significant performance gains with sound external verification.
  arXiv  Detail & Related papers  (2024-02-12T23:11:01Z)
• Bandit Linear Optimization for Sequential Decision Making and Extensive-Form Games [102.23975166536326]
  Tree-form sequential decision making (TFSDM) extends classical one-shot decision making by modeling tree-form interactions between an agent and a potentially adversarial environment. It captures the online decision-making problems that each player faces in an extensive-form game, as well as Markov decision processes and partially-observable Markov decision processes where the agent conditions on observed history. In this paper, we give the first algorithm for the bandit linear optimization problem for dilatedDM that offers both (i) linear-time losses and (ii) $O(sqrtT)$ cumulative regret in
  arXiv  Detail & Related papers  (2021-03-08T05:00:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.