ToM2Vec: Latent Theory-of-Mind Vectors Boost LLM Agent Cooperation by 9 Points
EliasEskin · x · 2026-10-23
New paper ToM2Vec trains LLM agents to latently model their partner's reasoning via continuous theory-of-mind vectors capturing multiple hypotheses, instead of explicitly verbalizing them.
- On Overcooked, ToM2Vec beats the Language ToM baseline by 9.0 points on average.
- Direct ToM probes show gains of 5.6 / 2.0 / 2.0 percentage points on predicting partners' beliefs, desires, and next actions over the strongest baselines.
- Trained only with a Qwen3-8B partner, the improvements transfer to unseen partner models, including frontier ones like GPT-5.4 and Gemma 4.
- Gains hold across 5 multi-agent tasks (cooperative and competitive).
More from coding & agent
- TURTLE paper auto-evolves tool-use benchmarks, boosting hard tasks on AppWorld by 165% — MichaelD1729 · 2026-10-24
- LangChain fixed its design agent's AI slop with skills, a design wiki, and guardrails — LangChain · 2026-10-24
- SplatLab: an autonomous research system that writes submission-ready 3DGS papers beating SOTA by up to +3.78 dB — zhenjun_zhao · 2026-10-24
- Chronos: a Postgres-compatible database where agent changes land only if they pass your policies — Antique-Willow-5841 · 2026-10-24
- Agent sandbox boat.dev hits 1,026 paying subscribers with $20/mo per-second-billed VMs — ycombinator · 2026-10-24
- Claude Code Team OS: put your whole product team's context in one shared repo — aakashgupta · 2026-10-24