From Single-Actor Environments to Multi-Actor Event Worlds: Can LLMs Be Event World Models?

Juntong Ni; Zewen Liu; Bohan Wang; Lige Zhang; Wei Jin

cs.AIOct 21, 2026

From Single-Actor Environments to Multi-Actor Event Worlds: Can LLMs Be Event World Models?

Authors: Juntong Ni, Zewen Liu, Bohan Wang, Lige Zhang, Wei Jin

Organizations: Emory University

Abstract

World models help agents assess the consequences of their actions before acting. Many real systems, however, involve multiple actors who make their own decisions, can evolve even when the agent takes no action, and are only partially observed through event logs. We formalize these systems as event worlds and ask whether large language models can predict future observations from the log and the agent's proposed actions. We build complementary benchmarks from human Diplomacy games and real Polymarket trades. Our hierarchical framework compares prediction with and without other actors' actions, then tests multi-step rollouts, predictions for actions never taken, and usefulness to agents. Fine-tuning and more data improve prediction when all actors' recorded actions are given. With only the agent's action, models struggle when other actors strongly affect the outcome, and larger models and longer histories help little. This gap also limits multi-step prediction and agent decisions, with models overestimating plan success. Yet imagined experience and initialization from world models can still improve policy learning. Anticipating other actors' actions remains a central challenge for event world modeling.

Figures & tables

Figure 1: From single-actor environments to multi-actor event worlds.

\mathcal{H}_{t}

, A , and

O

denote the event log, actions, and observations.

	Diplomacy	Polymarket
World type	board game	market
Actors $\mathcal{I}$	2 or 7 players	anonymous traders
Observation $O$	the board	trading statistics
Hidden part $X$	players’ intentions	order book, beliefs
Actions $A$	move, hold, support	buy or sell
Horizon $\Delta$	one phase	one hour

Table 1: The two event world benchmarks.

Task J (joint action)
		Diplomacy				Polymarket
Setting	Model	EM	EM high	EM low	F1	Acc	Acc high	Acc low	CRPS $\downarrow$
Zero-shot	GPT-6-Luna	29.1	3.4	55.2	90.8	43.0	36.8	48.0	0.42
	GPT-6-Sol	40.5	10.1	71.4	96.3	54.6	48.7	59.5	0.55
SFT	Qwen3-1.7B	59.7	23.6	96.4	96.9	66.1	62.5	69.0	0.29
	Qwen3-8B	65.1	30.8	100.0	97.7	65.5	60.5	69.5	0.29

Table 2: Single-step prediction (%, CRPS in cents) on decision points shared by all models, with every actor’s action given (Task J, Q1) or only the agent’s (Task S, Q2). EM high /Acc high and EM low /Acc low are restricted to high- and low-interaction transitions. Fine-tuned models (SFT) are evaluated zero-shot. Few-shot results are in Appendix E.1 . Bold marks the best prompted or fine-tuned LLM per column, baselines excluded.

Figure 2: The evaluation framework. The agent is orange, actors whose actions are hidden are dashed, and the dashed branch is an action never taken.

Figure 3: Scaling in training data and model size.

Figure 4: (a) Predicted probability that the Polymarket price does not change against the observed frequency. (b) Gain from knowing the other actors’ actions (Task J minus Task S) when the agent acts and when it is idle.

Figure 5: Task S against history length

K

. The full sweep is in Appendix F.1 .

		Diplomacy		Polymarket
Task	Model	F1 closed	F1 open	Acc closed	Acc direct
J	Qwen3-1.7B	91.9	97.5	60.2	64.4
	Qwen3-8B	94.1	97.9	61.2	63.8
	GPT-6-Luna	65.7	91.7	57.4	35.6
	GPT-6-Sol	83.4	96.4	57.4	55.6
S	Qwen3-1.7B	55.1	86.0	55.6	58.6

Table 3: Long-horizon rollout results. Diplomacy: F1 at step 5 when the model is fed its own predictions (closed loop) or the true board (open loop). Polymarket: Acc over 24 hours from recursive price prediction with logged trading activity (closed) or a direct forecast. Full table in Appendix G.1 .

	F1		Spurious $\downarrow$
Model	S	J	S	J
GPT-6-Luna	47.7	30.1	45.9	89.7
GPT-6-Sol	56.5	57.9	40.4	83.3
Qwen3-1.7B	44.0	73.0	51.5	33.1
Qwen3-8B	44.3	77.3	59.6	29.4

Table 4: Results after replacing the agent’s orders in Diplomacy (%). F1 compares predicted and true changes to units and supply centers. Spurious is the rate of predicting a change when original and modified orders produce the same board. More detailed results are reported in Appendix G.2 .

Figure 6: Success of plans made inside an LLM, judged inside the LLM and when replayed in the engine, against plans made in the engine.

Figure 7: Evaluation of candidate actions by LLMs in Diplomacy. (a) Gain in supply centers over

B{=}1

. (b) Predicted and realized gain of the chosen candidate.

Training data (Qwen3-1.7B policy)	$\Delta$ SC	Success (%)
Behavior policy (DipNet)	0.24	61.0
Real 1k	$-$ 0.58	47.5
Imagined 1k	$-$ 0.62	43.0
Real 1k + imagined 1k	$-$ 0.29	53.5
Real 2k	$-$ 0.23	54.0
Imagined 2k	$-$ 0.48	47.5

Table 5: Policies behavior-cloned on real or imagined games, or initialized from a world model.

\Delta

SC: mean change in supply centers over 10 phases.

Line of work	Main prediction or evaluation target	Relation to our study
Text, web, tool world models	Observations after an agent’s actions	We extend evaluation to logs with multiple actors whose future actions are unknown.
Visual and driving world models	Frames, scene states, or joint trajectories	Event logs can record actions and observations at irregular times.
Multi-agent benchmarks	Agents’ collaboration and competition	We evaluate world predictions from human game records and real market logs, then their usefulness to an agent.
Models of other actors	Other participants’ actions or beliefs	These predictions are one part of predicting the world’s future observations.
Event forecasting	Future events from records or news	Our predictions additionally condition on the agent’s proposed actions.
Offline model-based RL	Dynamics and policies learned from logged transitions	We examine the difficulty introduced by unknown actions of other actors.

Table 6: Related work compared by its prediction or evaluation target and its relation to event world modeling. Representative studies are discussed in Appendix A .

Appendix figures & tables20 assets

Supplementary material from the paper’s appendix.

Appendix

	Diplomacy	Polymarket
clock	phase counter	physical time in seconds
horizon $\Delta$	one phase	chosen; 1 h (also 5 min, 24 h)
actors $\mathcal{I}$	7 (or 2) players	taker wallets
action $A^{i}_{t+1}$	one order per unit; hold if none	0 to many orders (time, direction, size)
log $\mathcal{H}_{t}$	boards, orders, results	orders in earlier blocks
observation $O_{t}$	units, centers	prices, flow, depth proxies

Appendix

Table 7: How the general definition maps to the two worlds. Changed actions have engine-verified outcomes in Diplomacy. Polymarket provides an observational response check (Appendix G.3 ).

Question	Experiment	Evaluation reference	Diplomacy	Polymarket	Sec.
Q1: every action given	Does the model predict the next observation when every actor’s action is given?	the log	next board from all players’ orders	price move over the window from all orders	6.1
	Does more data or a larger model help, and is pretraining needed?	the log	5k to 320k transitions; 0.6B to 8B parameters; training from scratch	same	6.1
	Does the model know how much the world changes as time passes?	the log		horizons of 5 min, 1 h, and 24 h	6.1
	Does what the model learns hold when the world shifts?	the log	two-player games, unseen in training	markets that open after the training period	6.1
Q2: only the agent’s action	How much does knowing the other actors’ actions improve prediction?	the log	Task J vs. Task S, by interaction and when the agent issues no orders	Task J vs. Task S, including windows where the agent does nothing	6.2
	Do history, predicting the other actors’ behavior, or scale close the gap?	the log	up to 10 previous phases; factored variant, its orders resolved by the engine; data and model size	up to 10 previous hours; factored variant	6.2

Appendix

Table 8: The evaluation framework of Section 6 , one experiment per row.

Seed	J	S	SF	SF+engine	Top-1
42	59.7	20.1	22.2	23.1	47.6
43	59.6	19.6	21.5	22.1	46.8
44	60.7	19.9	23.1	23.4	48.1
Mean (sd)	60.0 (0.6)	19.8 (0.3)	22.2 (0.8)	22.9 (0.7)	47.5 (0.7)

Appendix

Table 9: Qwen3-1.7B fine-tuned on 20k Diplomacy transitions with three training seeds (%, EM except Top-1). SF first predicts the other players’ orders, then the next board, and SF+engine resolves its predicted orders in the engine (Appendix F.2 ). Top-1 is the share of the other players’ orders that the SF model predicts correctly, computed per sample and averaged over samples, with samples in which the other players issue no orders counted as correct. Per-order accuracy (Table 18 ) instead pools all units.

Task J (joint action)
		$K=0$				$K=3$
Setting	Model	EM	EM high	EM low	F1	EM	EM high	EM low	F1
Zero-shot	GPT-6-Luna	29.1	3.4	55.2	90.8	27.8	3.6	52.4	89.8
	GPT-6-Sol	40.5	10.1	71.4	96.3	53.3	18.8	88.3	96.5
Few-shot (3-shot)	GPT-6-Luna	27.6	1.6	54.0	89.8	23.2	1.4	45.4	89.1
	GPT-6-Sol	43.8	12.1	76.0	96.0	49.7	14.7	85.3	96.6

Appendix

Table 10: Single-step prediction in seven-player Diplomacy (%) on the shared subset (1,000 transitions, 2,000 Task S samples).

K

is the number of previous transitions given as history. EM high and EM low are restricted to high- and low-interaction transitions. Fine-tuned models are evaluated zero-shot, and baselines use no history. In the “+ engine” rows, the named policy supplies the other players’ orders and the engine resolves the joint action (Appendix D.3 ). Bold marks the best prompted or fine-tuned LLM per column, baselines excluded.

Task J (joint action)
		$K=0$					$K=3$
Setting	Model	Acc	Acc high	Acc low	Dir	CRPS	Acc	Acc high	Acc low	Dir	CRPS
Zero-shot	GPT-6-Luna	43.0	36.8	48.0	56.2	0.42	45.9	40.6	50.2	57.2	0.45
	GPT-6-Sol	54.6	48.7	59.5	56.5	0.55	55.4	51.3	58.8	57.6	0.63
Few-shot (3-shot)	GPT-6-Luna	44.1	41.1	46.5	56.4	0.41	41.6	37.1	45.3	56.6	0.39
	GPT-6-Sol	52.7	52.3	53.1	58.4	0.49	52.5	51.3	53.5	59.0	0.43

Appendix

Table 11: Single-step prediction in Polymarket (

\Delta=1

h, accuracies in %) on the shared subset (1,333 decision points).

K

is the number of previous hours given as history. Acc high and Acc low are restricted to high- and low-interaction windows. Dir is the direction accuracy on windows in which the mid-price changes. CRPS is in cents (lower is better). Fine-tuned models are evaluated zero-shot, and baselines use no history. Bold marks the best prompted or fine-tuned LLM per column, baselines excluded.

		Diplomacy (EM)		Polymarket (Acc)
Axis	Setting	J	S	J	S
Data (1.7B)	5k	48.9 (11.3)	16.2 (0.8)	62.0 (56.5)	56.6 (53.2)
	20k	59.7 (23.6)	20.1 (1.6)	66.1 (62.5)	59.9 (55.2)
	80k	74.7 (49.8)	23.0 (1.9)	69.5 (66.7)	61.8 (55.4)
	320k	88.4 (77.0)	25.4 (1.9)	71.6 (69.1)	64.9 (58.9)
Size (20k)	0.6B	57.6 (19.2)	20.5 (1.6)	63.3 (59.2)	58.1 (53.8)

Appendix

Table 12: Scaling the fine-tuned Qwen3 models in training data and model size (%, shared subsets). Values on high-interaction transitions are in parentheses.

		Diplomacy (EM)					Polymarket (Acc)
Data	Initialization	J	J high	J low	J, 2p	S	J	J, later	S
20k	pretrained	59.7	23.6	96.4	61.1	20.1	66.1	67.4	59.9
	random	32.0	4.6	59.9	0.3	10.2	60.8	59.6	57.8
320k	pretrained	88.4	77.0	100.0	88.4	25.4	71.6	74.0	64.9
	random	66.2	32.9	100.0	11.0	24.1	67.5	65.4	61.7

Appendix

Table 13: The Qwen3-1.7B architecture, fine-tuned from the pretrained checkpoint or trained from random initialization (%,

K=0

). J high , J low : high- and low-interaction transitions. J, 2p: Task J on the two-player common evaluation set. J, later: Task J on 1,333 decision points of the later markets. The other columns use the shared subsets.

Diplomacy, Task J
	Qwen3-1.7B		Qwen3-8B		Baseline
Split	All	High	All	High	All	High
7p	60.9	22.9	65.7	30.7	52.0	4.0
2p	61.1	38.6	69.6	53.0	53.1	23.9
Diplomacy, Task S
7p	19.7	1.2	19.8	1.2	7.3	1.5

Appendix

Table 14: Robustness on the common evaluation sets of Appendix B.3 (EM in Diplomacy, Acc in Polymarket, %). High: high-interaction transitions. 7p: seven-player games. 2p: two-player games, unseen in training. Test: the in-distribution test split. Later: the later-market split. Baselines: orders applied literally in Diplomacy (in Task S only the agent’s own), LightGBM in Polymarket.

	Outcome known		Acc, test $\to$ later
Model	Test	Later	Task J	Task S
GPT-6-Luna	81.9	1.6	43.0 $\to$ 46.7	46.1 $\to$ 48.5
GPT-6-Sol	68.1	0.0	54.6 $\to$ 57.5	48.5 $\to$ 52.6
Qwen3-1.7B (SFT)	–	–	66.1 $\to$ 67.4	59.9 $\to$ 61.4
Qwen3-8B (SFT)	–	–	65.5 $\to$ 70.7	60.2 $\to$ 63.1
LightGBM	–	–	68.8 $\to$ 67.1	61.4 $\to$ 61.8

Appendix

Table 15: Left: share (%) of resolved markets whose outcome each GPT-6 model says it knows (238 test and 440 later markets). Among test markets whose outcomes the models say they know, accuracy is 97.9% for GPT-6-Luna and 98.8% for GPT-6-Sol. Right: Task J and Task S Acc (%) on the 1,333-point subsets of the in-distribution test split and the later-market split.

		Diplomacy (EM)					Polymarket (Acc)
Model	Task	$K=0$	$K=1$	$K=3$	$K=6$	$K=10$	$K=0$	$K=1$	$K=3$	$K=6$	$K=10$
Qwen3-1.7B (SFT)	J	58.9	59.4	59.6	60.1	59.7	65.5	66.5	66.8	66.2	66.5
	S	19.9	22.2	21.9	21.1	20.8	60.5	60.8	61.9	61.8	61.1
	S, low	38.8	43.6	42.8	41.2	40.7	63.8	63.8	65.0	64.9	63.7
	S, high	1.3	1.2	1.3	1.2	1.2	56.5	57.2	58.0	58.0	58.0
GPT-6-Sol	J	40.5	47.4	53.3	54.5	51.7	54.6	56.3	55.4	54.1	54.8

Appendix

Table 16: History-length sweep on the shared subsets (EM in Diplomacy and Acc in Polymarket, in %). All models are evaluated zero-shot.

K

is the number of previous transitions or hours in the input. “S, low” and “S, high” restrict Task S to low- and high-interaction transitions.

	Diplomacy (EM)					Polymarket (Acc)
Model	J	S	SF	SF+engine	Share	J	S	SF	Share
GPT-6-Luna (zero-shot)	29.1	6.7	9.3	17.2	0.24	43.0	46.1	47.6	$-$ 0.06
GPT-6-Sol (zero-shot)	40.5	7.5	11.9	17.1	0.36	54.6	48.5	52.6	0.12
Qwen3-1.7B (SFT)	59.7	20.1	22.2	23.1	0.50	66.1	59.9	60.4	0.16
Qwen3-8B (SFT)	65.1	20.8	22.9	23.4	0.56	65.5	60.2	–	0.13
DipNet policy + engine	–	–	–	24.7	–	–	–	–	–

Appendix

Table 17: Prediction with and without the other actors’ actions. SF adds predictions of their behavior to the Task S output, and SF+engine resolves its predicted orders in the engine. Share

=(\mathrm{Err}_{S}-\mathrm{Err}_{J})/\mathrm{Err}_{S}

, with Err the error rate, is the relative reduction in error rate from Task S to Task J.

Model	All units	Interacting	EM high
Most frequent order	22.6	16.2	0.1
GPT-6-Luna (zero-shot)	16.8	10.9	1.5
GPT-6-Sol (zero-shot)	20.7	16.5	0.1
Qwen3-1.7B (SFT, 3 seeds)	29.6	25.5	1.9
Qwen3-8B (SFT)	30.7	26.6	1.8
Qwen3-1.7B (SFT), $K=3$	36.1	31.9	1.8

Appendix

Table 18: Per-order accuracy (%) of the SF models and two baselines on the other players’ orders in the 2,000 Task S samples of the shared subset, over all units and over interacting units. EM high is the high-interaction EM after the engine resolves the predicted orders.

	Task S EM			Others’ orders
Model	none	messages	blank	SF	SF + msg.
Qwen3-1.7B, press-tuned	18.3	18.2	17.6	47.0	47.9
GPT-6-Sol	8.9	11.1	10.2	31.8	32.9
GPT-6-Luna	6.8	6.9	7.1	26.3	26.2

Appendix

Table 19: Task S in press games (%, prompted models zero-shot). EM is given without the agent’s messages, with them, and with their text blanked. Others’ orders gives SF Top-1 (Table 9 ), without and with messages.

	Retreat		Adjustment		Both
Model	idle	acting	idle	acting	idle	acting
GPT-6-Luna (zero-shot)	23.0	9.0	77.8	70.0	38.6	49.1
GPT-6-Sol (zero-shot)	35.8	17.9	92.4	91.8	51.9	66.5
Qwen3-1.7B (SFT)	45.6	18.7	80.7	82.5	55.6	60.6
Qwen3-8B (SFT)	47.7	23.9	85.4	82.5	58.4	62.4

Appendix

Table 20: Diplomacy, Task J minus Task S EM (points) when the agent issues no orders (idle) or some (acting), by phase type. Retreat phases have 430 idle and 134 acting samples, and adjustment phases 171 and 257.

		Diplomacy, 5-step chains				Polymarket, 24 hours
Task	Model	EM closed	EM open	F1 closed	F1 open	Acc closed	Acc direct
J	Qwen3-1.7B (SFT)	5.6	65.4	91.9	97.5	60.2	64.4
J	Qwen3-8B (SFT)	13.2	68.8	94.1	97.9	61.2	63.8
J	GPT-6-Luna	0.0	42.2	65.7	91.7	57.4	35.6
J	GPT-6-Sol	0.2	57.2	83.4	96.4	57.4	55.6
S	Qwen3-1.7B (SFT)	0.0	22.0	55.1	86.0	55.6	58.6

Appendix

Table 21: Multi-step prediction (%), extending Table 3 . Diplomacy scores the board at step 5 with predicted boards (closed loop) or recorded boards (open loop) as inputs. Polymarket recursively predicts prices with logged trading activity (closed) or forecasts 24 hours directly. Always predicting a fall gives 49.4% Acc.

	Task S form (other actors imagined)				Task J form (other actors given)
Model	F1	Insensitive $\downarrow$	Spurious $\downarrow$	Size pred/ref	F1	Insensitive $\downarrow$	Spurious $\downarrow$	Size pred/ref
GPT-6-Luna (zero-shot)	47.7	6.0	45.9	3.4/3.9	30.1	0.1	89.7	9.5/3.9
GPT-6-Sol (zero-shot)	56.5	4.8	40.4	3.9/3.9	57.9	0.3	83.3	7.6/3.9
Qwen3-1.7B (SFT)	44.0	6.0	51.5	5.4/3.9	73.0	3.2	33.1	4.3/3.9
Qwen3-8B (SFT)	44.3	5.6	59.6	5.6/3.9	77.3	2.9	29.4	4.3/3.9

Appendix

Table 22: Diplomacy action changes, extending Table 4 , on 5,040 order-set evaluations from the shared subset (%, except Size). F1 and Insensitive cover alternatives that change the next board. Spurious covers alternatives that do not, excluding controls that repeat the original orders. Size reports the mean predicted and true numbers of changes to units and centers across all evaluations.

Model	Sign	Insensitive $\downarrow$	Magnitude	Monotonicity
GPT-6-Luna (zero-shot)	93.6	6.9	1.74	0.20
GPT-6-Sol (zero-shot)	84.1	15.4	2.94	0.21
Qwen3-1.7B (SFT)	52.2	41.4	0.77	0.12
Qwen3-8B (SFT)	52.3	34.2	0.93	$-$ 0.02

Appendix

Table 23: Polymarket price-response checks in Task S (%, except Magnitude and Monotonicity). The first three columns reverse all of the agent’s orders. Sign measures agreement with the nonzero reference response, counting a zero prediction as a miss. Insensitive counts predicted responses smaller than 0.0005 in absolute value. Magnitude is the ratio of mean absolute predicted to reference responses. Monotonicity instead removes the orders and computes Spearman correlation between relative order volume and the predicted effect of including them, with its sign oriented by the anchor order’s buy or sell direction.

Task	Model	WM	W2R	CR
J	Qwen3-1.7B (SFT)	55.8	50.8	0.78
J	Qwen3-8B (SFT)	55.6	50.6	0.78
J	GPT-6-Luna	18.2	34.2	0.53
J	GPT-6-Sol	41.0	41.4	0.64
S	Qwen3-1.7B (SFT)	82.8	41.2	0.63
S	Qwen3-8B (SFT)	82.8	42.2	0.65

Appendix

Table 24: Plan consistency on 500 starts. WM is success inside the world model, and W2R is success when its plan is replayed in the engine (both in %). CR is W2R/Real, where Real

=65.0\%

is success when the agent acts directly in the engine.

Agent	Task	Real	WM	W2R	CR
Supervised	J	65.0	55.8	50.8	0.78
	S	65.0	82.8	41.2	0.63
RL	J	67.4	55.6	50.2	0.74
	S	67.4	85.2	46.4	0.69

Appendix

Table 25: Plan consistency of the Qwen3-1.7B world model (20k) with a supervised or an RL-trained DipNet agent (success rates in %, 500 starts).

Training data	Real	Imagined	Pairs
Real 2k	2,000	0	12,974
Real 1k + imagined 1k	1,000	1,000	12,580
Imagined 2k	0	2,000	12,271

Appendix

Table 26: Successful real and imagined games and their board and order pairs for behavior cloning.

LLM World Models

Large language model world models predict how environments change so agents can plan, learn, and evaluate actions before execution.

See all 34 papers

Self-Evolving World Models for LLM Agent Planning
Jun 29, 2026Xuan Zhang, Wenxuan Zhang, See-Kiong Ng +1Test-Time Adaptation World Model Learning
National University of Singapore · Singapore University of Technology and Design · Singapore Management University
How do World Models and Policies Compose in LLM Agents? A Joint Spectral and Behavioral Account
Aug 30, 2026Ruize Xu, Xiao Yu, Yujin Tang +2World Model Learning World Models
Dartmouth College · Columbia University
Towards a Belief-Based World Model for LLM Agents
Aug 31, 2026Shubham Kumar, Harshit Kumar, Narendra Ahuja +1Belief-Space Planning Partially Observable RL
UIUC · IBM

Jun 29, 2026J/K move · Enter open · S save

Self-Evolving World Models for LLM Agent Planning

Xuan Zhang, Wenxuan Zhang, See-Kiong Ng, Yang Deng

National University of Singapore · Singapore University of Technology and Design · Singapore Management University

Test-Time Adaptation World Model Learning World Models World Model-Based Planning LLM Agent Planning Memory-Augmented Language Model Agents

Open paper AskPDF arXiv

World models offer a principled way to equip long-horizon LLM agents with foresight: predictions of action consequences before execution. However, unreliable foresight can be ignored, misused, or even degrade downstream decision-making. In this paper, we introduce WorldEvolver, a self-evolving world model framework that revises its deployment-time context while keeping the downstream agent and all model parameters frozen. WorldEvolver integrates three modules: (i) Episodic Memory, which exploits real action transitions through retrieval-based simulation; (ii) Semantic Memory, which extracts persistent heuristic rules from prediction-observation mismatches; and (iii) Selective Foresight, which filters low-confidence predictions before integrating them into agent reasoning context. We evaluate WorldEvolver on ALFWorld and ScienceWorld, measuring world model prediction accuracy on Word2World and downstream agent success rate on AgentBoard. Extensive experiments show that WorldEvolver achieves the highest prediction accuracy across three backbones and leads other world model baselines on downstream agent success rate, demonstrating that test-time memory revision enhances both predictive fidelity and planning performance.

Abstract

LLM World Models

Explore similar work

Self-Evolving World Models for LLM Agent Planning

How do World Models and Policies Compose in LLM Agents? A Joint Spectral and Behavioral Account

Towards a Belief-Based World Model for LLM Agents