Research map / Multi-agent systems and games / LLM agents
EvoCF: Multi-Agent Collaboration via Agentic Memory-Driven Evolutionary Counterfactual Planning
Haotian Chi, Zeyu Feng, Xingrui Yu, Linbo Luo, Yew-Soon Ong, Ivor Tsang, Hechang Chen, Yi Chang, Haiyan Yin
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes EvoCF, an agentic memory-driven evolutionary counterfactual planning framework for discovering multi-agent collaboration strategies for embodied systems via counterfactual plan generation.
Problem
LLM-based planners for multi-agent embodied systems often fail to capture the physical and coordination constraints of real-world environments when planning collaboration strategies.
Approach
Combines agentic memory with evolutionary search over counterfactual plans so that the planner can generate and refine alternative collaboration strategies, as described in the abstract.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add memory-guided counterfactual plan generator (vs random mutations) (ablation) | EvoCF · MAP-THOR (2 agents) | success rate: 0.68 -> 0.84 | Improved |
| add agentic memory-driven evaluator (vs heuristic evaluator) (ablation) | EvoCF · MAP-THOR (2 agents) | success rate: 0.72 -> 0.84 | Improved |
| add symbolic constraint inductor (ablation) | EvoCF · MAP-THOR (2 agents) | success rate: 0.75 -> 0.84 | Improved |
| add memory-guided counterfactual generator, steps (ablation) | EvoCF · MAP-THOR (2 agents) | average steps: 21.37 -> 18.69 | Improved |
| increase retrieved trajectories K from 1 to 5 (ablation) | EvoCF evaluator · MAP-THOR (2 agents) | success rate: 0.77 -> 0.84 | Improved |
| increase retrieved trajectories K from 5 to 10 (ablation) | EvoCF evaluator · MAP-THOR (2 agents) | success rate: 0.84 -> 0.82 | Hurt |
| scale number of agents from 2 to 3 | EvoCF · MAP-THOR | success rate: 0.84 -> 0.87 | Improved |
| scale number of agents from 3 to 4 | EvoCF · MAP-THOR | balance: 0.81 -> 0.74 | Hurt |
| inject transferred constraints into planner (put pots and pans task) | Planner · MAP-THOR put pots and pans on stove | success rate: 0.60 -> 0.80 | Improved |
| inject transferred constraints into planner (open all drawers task) | Planner · MAP-THOR open all drawers | success rate: 0.40 -> 0.60 | Improved |
| use EvoCF instead of LLaMAR with Claude 3.5 Sonnet | LLaMAR · MAP-THOR (2 agents) | success rate: 0.70 -> 0.81 | Improved |
| use EvoCF instead of LLaMAR with GPT-4o mini | LLaMAR · MAP-THOR (2 agents) | success rate: 0.61 -> 0.74 | Improved |
Closest papers by meaning
- From Assumptions to Actions: Turning LLM Reasoning into Uncertainty-Aware Planning for Embodied Agents (ICLR 2026 · similarity 0.88)
- Mosaic: Runtime-Efficient Multi-Agent Embodied Planning (ICML 2026 · similarity 0.88)
- Learning to Share: Selective Memory for Efficient Parallel Agentic Systems (ICML 2026 · similarity 0.88)
- Collaborative Tree Search for Enhancing Embodied Multi-Agent Collaboration (CVPR 2025 · similarity 0.87)
- G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems (NeurIPS 2025 · similarity 0.87)
- MemEvolve: Meta-Evolution of Agent Memory Systems (ICML 2026 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
