arXiv:2608. 08960v1 Announce Type: new Abstract: Multi-step language-model agents repeatedly process growing interaction histories, leading to substantial context costs.
arXiv:2608.29897v1 Announce Type: new Abstract: Long-horizon agents need a context manager to compress growing interaction histories into a bounded working context, via passive strategies or active s...
arXiv:2601.04786v3 Announce Type: replace-cross Abstract: Recent advances in large language models (LLMs) enable agentic systems trained with reinforcement learning (RL) over multi-turn interaction,...
The paper introduces LOHA, a context layout that compresses older tool observations into soft tokens while keeping the agent’s own turns and the last K observations in plain text, and ACD, a training method that distills full‑text predictions into this latent representation while anchoring behavior on plain text. This approach reduces context per call by up to 57% without significant loss in resolve rates, and improves instance throughput in single‑GPU serving. Experiments on SWE‑bench Verified show that K=3 yields a 43–57% compression with only modest performance impact, while larger windows favor task performance over compression.
MemBodied introduces a fixed‑size episodic memory for Vision‑Language‑Action models, comprising an associative state that tracks interactions across policy calls and an episode anchor that stores a compact representation of the initial scene. By conditioning action generation on these memory components instead of raw past observations, MemBodied reduces context bloat and inference latency. In five memory‑dependent RMBench tasks, it outperforms stateless and vanilla recurrent policies by significant margins, and achieves a 90.6% success rate on the LIBERO‑Long suite, improving over the baseline by 5.4%.
arXiv:2609.32353v2 Announce Type: replace Abstract: Visual token reduction is an effective way to accelerate multimodal large language models (MLLMs), but performance deteriorates rapidly under extre...
Multi-task manipulation policies differ in architecture, scale, and pretrained priors all at once, so published comparisons cannot attribute performance to any single component. We argue that most of...
arXiv:2610.08183v1 Announce Type: cross Abstract: Multi-task manipulation policies differ in architecture, scale, and pretrained priors all at once, so published comparisons cannot attribute performa...
The paper introduces GLANCE, a one‑pass block drafting method that enables lossless speculative decoding for vision‑language models. By using a block‑diffusion head that reads the fused vision‑language state, GLANCE eliminates the need for the drafter to process the image at every step, allowing it to fill an entire block in a single forward pass. Experiments show that GLANCE can decode up to 2.93× faster than autoregressive decoding while maintaining exact greedy decoding results across multiple tasks.
arXiv:2607. 25487v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models translate natural-language commands into robot action sequences, but leading systems on the LIBERO-Plus robustness benchmark use three- to seven-billion-parameter backbones whose memory demands can exceed embedded robotic budgets.
StateComp introduces a method for long‑horizon agents to decide when to compress historical interactions based on the current agent state, rather than relying on fixed windows or periodic schedules. The framework uses a two‑stage annotation process to create KEEP and READY labels, trains an imbalance‑aware router on frozen language model representations, and groups adjacent READY interactions into compact summaries. Experiments on WorkBuddyBench show that StateComp cuts agent and summarization tokens by 52.27% and speeds up representation extraction 12.67‑fold while preserving task performance.
The paper introduces LRE (Learned Relevance Eviction), a lightweight, CPU‑only, language‑model‑free scorer that learns which parts of an agent’s interaction history are task‑critical and preserves them verbatim. In experiments, LRE matches or surpasses baseline eviction policies on accuracy‑cost trade‑offs, recovers 93% of full‑history accuracy, reduces worst‑case prompt size by 52%, and outperforms dense and token‑pruning encoders in conversational memory while being 295–1569× smaller. The method also achieves superior budgeted answer quality on LoCoMo reading and can be trained annotation‑free, recovering 95% of supervised scorer performance.
arXiv:2606.18974v3 Announce Type: replace Abstract: Unified multimodal models (UMMs) interleave generated ''visual thoughts'' (VTs) with text reasoning to improve spatial tasks. This incurs roughly a...