# COUNTERMEM: World-Model Verified Counter-Factual Memory for Language Agents

arXiv: https://arxiv.org/abs/2609.31874 · HTML: https://mlsanity.com/paper/2609.31874/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in World models for language agents, one of 11 directions in World models.
- Builds on 25 of its 35 references that are in the map.
- First posted on arXiv 25 Sep 2026.

## Placed in

- World models / [World models for language agents](https://mlsanity.com/wm/world-models-for-language-agents/)
- LLM agents and tool use / [Agent memory systems](https://mlsanity.com/agents/agent-memory-systems/)

## Builds on (most cited first, 25 of 25)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [Dream to Control: Learning Behaviors by Latent Imagination](https://mlsanity.com/paper/1912.01603/) (2019)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [Learning Latent Dynamics for Planning from Pixels](https://mlsanity.com/paper/1811.04551/) (2018)
- [Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task](https://mlsanity.com/paper/1809.08887/) (2018)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [ExpeL: LLM Agents Are Experiential Learners](https://mlsanity.com/paper/2308.10144/) (2023)
- [Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs](https://mlsanity.com/paper/2305.03111/) (2023)
- [MiniF2F: a cross-system benchmark for formal Olympiad-level mathematics](https://mlsanity.com/paper/2109.00110/) (2021)
- [Agent Workflow Memory](https://mlsanity.com/paper/2409.07429/) (2024)
- [ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory](https://mlsanity.com/paper/2509.25140/) (2025)
- [ProofNet: Autoformalizing and Formally Proving Undergraduate-Level Mathematics](https://mlsanity.com/paper/2302.12433/) (2023)
- [SWE-Search: Enhancing Software Agents with Monte Carlo Tree Search and Iterative Refinement](https://mlsanity.com/paper/2410.20285/) (2024)
- [Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigation](https://mlsanity.com/paper/2410.13232/) (2024)
- [DafnyBench: A Benchmark for Formal Software Verification](https://mlsanity.com/paper/2406.08467/) (2024)
- [Verus: Verifying Rust Programs using Linear Ghost Types (extended version)](https://mlsanity.com/paper/2303.05491/) (2023)
- [BugsInPy: A Database of Existing Bugs in Python Programs to Enable Controlled Testing and Debugging Studies](https://mlsanity.com/paper/2401.15481/) (2024)
- [Code World Models for General Game Playing](https://mlsanity.com/paper/2510.04542/) (2025)
- [A benchmark for vericoding: formally verified program synthesis](https://mlsanity.com/paper/2509.22908/) (2025)
- [Executable Counterfactuals: Improving LLMs' Causal Reasoning Through Code](https://mlsanity.com/paper/2510.01539/) (2025)
- [Construction-Verification: A Benchmark for Applied Mathematics in Lean 4](https://mlsanity.com/paper/2602.01291/) (2026)

## Abstract (arXiv)

Existing agent memory frameworks mainly create memory through an agent's interaction with the factual world, e.g., remembering feedback from actions taken to improve performance on future tasks. However, these frameworks seldom ask the "what if" question during memory construction: what if a different action had been taken, would the feedback have changed, and how could this feedback become useful memory? Obtaining such feedback directly in an active environment can be expensive and can alter the state needed for comparison. In this work, we introduce COUNTERMEM, a reinforcement-learning framework for constructing and using verified counterfactual memory across tasks. After a failed action, COUNTERMEM evaluates local alternatives from a copy or reset of the original state using executable world models, such as tests, proof checkers, and solvers. It stores improvements with the original and corrected actions, checked outcomes, and conditions for reuse. A learned memory-use policy selects a retrieved record or skips memory to balance task success and interaction cost, while the base LLM remains fixed. Both memory and policy are frozen during held-out evaluation. We evaluate COUNTERMEM on 12 benchmark settings across six domains. With gpt-oss-120b, COUNTERMEM improves both ReAct and Reflexion on all 12 benchmarks across six domains, averaging a gain of 12.6 percentage points over their unaugmented versions. In the four-domain comparison across two backbones, task-run tokens decrease by 7.7-42.0%, excluding offline selector-training costs. Further analyses show that removing verification or persistent storage weakens the gains, while applying verified corrections to unsuitable decisions can reverse them. Code will be released upon acceptance.