News without the noise
Memory architectures, long-horizon reasoning
28 articles
Hu et al. test whether long-horizon robot manipulation requires memory inside the action policy itself. On LIBERO-Mem, their architecture places all interaction history in a multimodal agent and achieves 76.3% average completion with an episodically stateless action model, versus 14.8% for the strongest reported baseline.
Lum and Zhang implemented a shared-memory abstraction in AIOS where agents record structured memories but the system kernel controls how those memories are retrieved and inserted into prompts. Across 1,800 trials with three language models, their approach substantially outperformed unmanaged and standard retrieval-based memory while approaching full-context performance at lower computational cost.
Li and Li introduce RD-Forget, a training-free memory framework that separates long-term storage from the evidence used to answer each query. Across five memory and reasoning settings, the authors report that query conditioning and selective suppression of superseded facts improve answers while preserving access to historical information.
Zhang et al. introduce ConvMem, a training-free framework that uses prompted language models as query-dependent summarization kernels over segments of long documents. On two synthetic long-context, multi-hop question-answering benchmarks, the authors report better performance than training-free baselines and stronger out-of-distribution behavior than reinforcement-learning-trained memory methods.
Yang et al. developed MeClear to identify retrieved memories that impair an LLM agent, including outdated, misleading, or mutually conflicting evidence. Across ten long-dialogue memory pools, the framework achieved 85.9% target recall and an 82.3% task recovery rate, improving recovery by 25.5 percentage points over a leave-one-out baseline.
Duesterwald et al. evaluate reliability by running the same AppWorld task five times, exposing a substantial difference between average success and repeatable success. Their self-evolving framework stores targeted guidelines about unstable trajectory steps, increasing five-for-five task success by 16 percentage points on repeated tasks and 13 points on similar tasks.
Geng, Wang and Yuan developed a compact-memory pipeline that merges related memories online and packs retrieved information into the prompt as grouped units. On two long-horizon memory benchmarks, the authors report better quality–token trade-offs than several streaming and retrieval baselines, with the strongest results in the 2,000–5,000-token range.
Goyal and Ray tested whether four forms of agent memory remained usable after changing the model that writes or reads them. Across 48 synthetic histories, fixed-schema knowledge graphs transferred with almost no accuracy change, whereas compressed notes were strongly coupled to migration direction and partially updated retrieval indexes recovered less than half the benefit of full re-embedding.
The authors introduce LatentStream, a progressive latent working-memory framework for multimodal LLMs processing streaming video. Instead of storing historical clips in an external memory bank and retrieving them as extra visual context, LatentStream converts retrieved evidence into compact, fixed-length latent memory tokens that evolve over time. Experiments show the method outperforms prior store-and-retrieve approaches on both online and offline video understanding benchmarks.
Fan introduces VestigeKV, a training-free method for compressing the actively attended KV cache in a NoPE multi-head latent attention model. On needle-retrieval tests spanning 8,000 to 65,000 tokens, it preserves perfect retrieval at 8× compression and scores 0.92 at 32×, while moving rather than deleting excluded cache rows.
Liu, Wang, and Bie developed an agent that learns traffic-simulation workflows through autonomous exploration rather than updating its underlying language model. Across two held-out benchmarks and three backbone LLMs, SimSkill increased independently verified task completion by as much as 25 percentage points, although gains varied by model and inference budget.
The authors developed RuleMem, a memory framework that induces reusable natural-language rules from dispersed conversational history rather than storing only isolated facts. Across two long-term conversation benchmarks, it achieved the highest reported accuracy on LoCoMo and exceeded the average of 14 baselines by 27.47 percentage points.
Dai et al. study how bounded agents decide which concepts and structures are worth building into persistent models. Across three experiments, their Representational Empowerment objective favored representations that supported future modeling and planning, outperforming information-gain alternatives and ablated baselines.
The authors analyzed archived coding-agent trajectories to determine how instructions, artifacts, tool outputs, and agent-generated state differ in retention and compression. Tests of object-aware compression and retrieval-based memory policies found that calibration results did not necessarily generalize to held-out tasks, while nominally equal token budgets produced unequal context and system costs.
Shi and colleagues introduce S³Gym, a benchmark that separates open exploration from held-out evaluation to test whether language-model agents can examine, assess, and learn from their own behavior. They find that experience can improve later decisions, but gains vary substantially by model, game, and whether experience is retained as raw history, compressed into summaries, or incorporated through parameter training.
Tang et al. introduce WikiSkill, a framework that separates raw agent experience, accumulated knowledge, and executable skills instead of leaving useful insights scattered across optimization histories. Across multiple benchmarks and models, the authors report that this persistent wiki improves skill evolution and enables skills to transfer between models and model families.
Chen et al. replace the repeatedly updated text memory used by recommendation agents with a vector memory built from collaborative interaction data. Across four instruction-grounded benchmarks, their system matched or surpassed the strongest collaborative text-memory agent in 19 of 20 metric cells while eliminating per-interaction LLM calls for memory maintenance.
Li and colleagues formulate multimodal memory retrieval as an optimization problem: selecting a budget-constrained forest of relevant memories and reliable relationships. Across four long-term multimodal memory benchmarks, the authors report improved accuracy with multiple foundation models and a better trade-off between performance and lifecycle cost.
VoiceMem is a dual-stream memory architecture for duplex speech language models, pairing a factual left brain for personal information with an emotional right brain for affect and persona. The authors show that top-5 retrieval beats Mem0 at top-200 by nearly 30 points, and that retrieval completes in 134 ms, within voice-activity-detection latency. The result is a practical memory foundation for real-time, personalized, emotionally aware spoken interaction.
Muennighoff et al. observe that during long reasoning traces, most intermediate tokens lose importance as the model continues. They propose Prefix Sliding, which keeps only the instruction prefix and a recent window of tokens, discarding the rest to cap memory usage. Applied without training to existing models, it achieves up to 3x speedup with no performance loss; training with it enables reasoning traces beyond 100,000 tokens.
Huang et al. replace per-query iterative action optimization with a learned trajectory prior conditioned on current and goal images. Across four goal-conditioned pixel-control benchmarks, the authors report higher success rates and an order-of-magnitude reduction in planning time.
The authors formalize the trade-off between retaining raw memory and consolidating it via compression, showing that consolidation improves accuracy by up to 48% under tight context budgets, while retention is preferable when budgets are generous. They propose OAS, a lightweight learner that selects the optimal operator per query.
The authors introduce COMFYCLAW, an agentic harness that controls ComfyUI workflows for image generation. By representing workflow construction as typed graph editing, reverting invalid edits, and using a region-level vision-language model (VLM) verifier to provide actionable repair suggestions, COMFYCLAW evolves a skill library from past trajectories, errors, and verifier feedback. Across four benchmark splits, three agent models, and two image backbones, COMFYCLAW achieves the best average evaluation score in all six agent configurations, and human annotators prefer its outputs over variants without skill evolution.
The authors introduce AutoMem, a framework that treats memory management as a learnable skill for LLMs by promoting file-system operations to first-class actions. By automating the optimization of memory structure (prompts, schemas, action vocabulary) and model proficiency (training on good memory decisions), AutoMem improved base agent performance by approximately 2x to 4x across three long-horizon games without altering task-action behavior.
Zhang et al. propose a training paradigm that equips LLM agents with an internal world model for prospective reasoning. By first injecting predictive capabilities through a world model mid-training stage, then eliciting structured foresight via supervised fine-tuning, and finally calibrating with reinforcement learning, the authors demonstrate significant improvements on search and mathematical reasoning tasks over standard fine-tuning approaches.
Kim et al. introduce Multi-Agent Transactive Memory (MATM), a framework for storing and retrieving agent-generated trajectories in a shared repository accessible to a population of LLM agents. In ALFWorld and WebArena environments, retrieving prior trajectories improves downstream task success rates and requires fewer interaction steps without any coordination or joint training.
The authors present the first systems-level characterization of LLM agent memory systems. They introduce a taxonomy, build a phase-aware profiler, and evaluate ten systems across two benchmarks, showing how design choices shift computational costs between memory construction and retrieval. Key recommendations include construction scheduling and amortization via query volume.
The authors propose MAGE, a memory system that treats an agent's history as an execution-state tree rather than a semantically organized document store. On the MemoryArena benchmark, MAGE raised average task success by 7.8–20.4 percentage points over RAG-based baselines while cutting token use by 55.1%.