Eric Horvitz

Reasoning models think in long, unstructured streams with no mechanism for compressing or organizing their own intermediate state. We introduce MEMENTO: a method that teaches models to segment reasoning into blocks, compress each block into a \emph{memento}, i.e., a dense state summary, and reason forward by attending only to mementos, reducing context, KV cache, and compute. To train Memento models, we release OpenMementos, a public dataset of 228K reasoning traces derived from OpenThoughts-v3, segmented and annotated with intermediate summaries. We show that a two-stage SFT recipe on OpenMementos is effective across different model families (Qwen3, Phi-4, OLMo3) and scales (8B--32B parameters). Trained models maintain strong accuracy on math, science, and coding benchmarks while achieving ${\sim}2.5\times$ peak KV cache reduction. We extend vLLM to support our inference method, achieving up to $2\times$ throughput improvement while also enabling us to perform RL and further improve accuracy. Finally, we identify a \emph{dual information stream}: information from each reasoning block is carried both by the memento text and by the corresponding KV states, which retain implicit information from the original block. Removing this channel drops accuracy by 15pp on AIME24.

The trajectory of AI development suggests that we will increasingly rely on agent-based systems powered by language models, composed of independently developed agents with different information, privileges, and tools. The success of these systems will depend critically on effective collaboration among these heterogeneous agents, even under partial observability. Despite intense interest, the literature lacks empirical studies evaluating agentic collaboration without relying on fixed communication protocols, limiting insights for open-world deployments. We propose an illustrative collaborative maze-solving benchmark that (i) isolates collaborative capabilities, (ii) modulates problem complexity, (iii) enables scalable automated grading, and (iv) imposes no output-format constraints, benchmarking unguided, natural communication. Using this benchmark, we evaluate 32 leading open- and closed-source models in solo, homogeneous, and heterogeneous pairings. Our results reveal a surprising _collaboration gap_: models that perform well solo often degrade substantially when required to collaborate. We identify mitigations that show remarkable influence. For example, a small nudge via a _relay inference_ approach, where a stronger agent leads before handing off to a weaker one, closes much of the gap. Our findings argue for (1) collaboration‑aware evaluation, (2) training strategies to enhance collaborative capabilities, and (3) deliberate interaction design to elicit agents' collaboration skills, principles relevant to AI-AI and human-AI settings where agents must establish common ground.