StateMem is presented, a state-first memory method that explicitly tracks supersession and relational dependencies, and it is shown it improves current-state accuracy over the strongest same-backbone baseline and over the strongest memory system, while remaining competitive with the long-context baselines.
Abstract
As LLM-based agents are deployed for longer and higher-stakes tasks, their memory systems continue to have crucial gaps. While existing memory benchmarks focus largely on recall-shaped tasks, we argue an effective memory system must track the evolving state of the world; as facts, constraints, and decisions are revised over a long interaction, answers must reflect the current state and not a superseded one. We define this capability as state tracking and instantiate it in StateMemBench, a benchmark of 234 multi-session scenarios spanning two conversation-length regimes. Its closed-pool grading scores whether an answer reflects the current state, the superseded state, or fails otherwise, separating state-tracking failures from other errors by construction. Our analysis shows that this task is challenging for existing memory systems, retrieval-augmented baselines, and long-context baselines. We then present StateMem, a state-first memory method that explicitly tracks supersession and relational dependencies, and show it improves current-state accuracy over the strongest same-backbone baseline by 1.8x (0.205 ->0.363) on DeepSeek-V4-Flash and over the strongest memory system by 1.6x (0.149 ->0.233) on Qwen-3.5-9B, while remaining competitive with the long-context baselines. Finally, we show the same state approach can be applied as a lightweight single-call wrapper over existing memory systems, lifting current-state accuracy by +32 to +67 points on StateMemBench across six memory and retrieval backends. A length- and cost-matched control attributes +15 to +32 of those points to state structure rather than added context.
Experiments on long-horizon embodied and web-agent benchmarks show that MemPrism consistently improves the task performance, especially as trajectories become longer, while reducing memory token consumption.
Zhi-Sheng Chen, Bingfan Zeng, Bangde Cao et al.· 0 citations
TARL is introduced, a memory state update framework that maps each statement to one of five executable actions and is trained by comparing the memory states produced by alternative update operations, encouraging the model to select the operation that leads to the correct result.
Han Xiao, Hongjun Xu, Xin Zhang et al.· 0 citations
Memory-augmented agents can know that a user's stored state is outdated and still plan around the old value. The STALE benchmark calls this the implicit policy adaptation (IPA) gap. We identify one structural contributor: draft-anchored verification checks what a response says, and in an open-ended response the stale dependency is usually unsaid. StateAuditor therefore audits in the opposite direction, from stored state to draft. An LLM proposes candidate old-to-new transitions from timestamped evidence; deterministic code pins each quotation to a single entry, checks that the new evidence really is newer, and lets only these verified transitions trigger repair. What is verified is provenance and chronology - not semantic supersession. On STALE's full protocol (400 scenarios, 50-session histories, one independent response per query), strict single-query VTA scores .736 against .686 for our locked predecessor under the same judge: a +5.0-point paired gain (95% CI [+2.9, +7.2]) coming almost entirely from IPA and premise resistance (PR). The benchmark's own judge, from a third model family, reproduces the gain (.738 vs. .680). On an independent cross-family preference-evolution benchmark (HorizonBench), the full draft-audit-repair pipeline over a gold-derived structured store raises current-preference accuracy (user-clustered p<.01), though a matched control shows most of this external gain is the draft-side audit itself; a harder authored lifecycle set gives no gain, bounding the claim while false invalidation stays controlled. On STALE, by contrast, a matched control (same evidence, adapter, and call budget) scores only .692 (+0.6 over the predecessor, n.s.), attributing the STALE gain to the transition machinery rather than added context or calls. We make no claim about general-purpose agent memory.
LLM agents increasingly take on long-running tasks whose history grows far beyond a single model context window. Existing approaches compress earlier interactions or extract selected information into fixed memory representations, committing to what to preserve before future needs are known. We present Scroll, a context manager that treats each agent session as an executable Session Environment. The environment is backed by an append-only Event Log and a sandboxed, persistent Python kernel. The kernel maintains a typed namespace across model calls, allowing tool outputs, retrieved history, and derived state to be bound to variables rather than serialized into the prompt at each call. Model-written code searches, materializes, and transforms session state through exec; only explicitly printed projections enter the model's working view for the next call. Context management thus becomes a programming task that inherits the improving coding abilities of LLMs, while the Event Log preserves lossless historical ground truth. As the working view approaches its budget, stale spans are evicted but remain recoverable: an eviction index keeps compact landmarks tied to exact Event Log addresses, so that the agent navigates directly to evicted regions instead of searching the full log. With Qwen3.8-Max as the backbone, Scroll achieves 94.8% on LongMemEval_S; 73.1% on BEAM_10M, surpassing the best published memory system by 5.1 points; and 86.7% on LOCA_256K, exceeding the best published long-horizon agent by 37.4 points.
Generative world models are increasingly driven as simulators: a planner forks a state, rolls out futures, backtracks, and returns to a visited viewpoint. Recent benchmarks establish that current video world models fail this usage, and attribute it to the model, prescribing new architectures and training objectives. We show this attribution is incomplete, and for an important class of models simply wrong. Snapshotting the state the runtime already holds -- an observation plus RNG state, a memory bank, or a windowed KV context, by architecture -- and restoring it after a genuine excursion reproduces the never-left continuation byte-identically on all three; corrupting only the RNG degrades it. The capability was never missing: request-centric serving discarded it, inheriting from language-model serving the assumption that runtime state is recomputable -- but world-model state carries a non-recomputable kernel. We define Persistent Computational State (PCS), the minimal non-recomputable state that must survive across requests, show it can be discovered by measurement, and build a session-centric runtime over it. Checkpoint and restore cost 0.012 ms against a 1.85 s generation step; resident sessions become host- rather than device-bounded (measured to 1,024); and world memory must be evicted by relevance to the return, not recency -- the inverse of LLM practice.
Pro-LONG, a minimal context management framework built around programmatic memory for LLM agents in long-horizon, exploratory settings, is proposed, which addresses the tradeoff of preserving more information makes retrieving relevant details less tractable.
A. Fox, Jun-Lin Wang, P. Rosu et al.· arXiv.org· 2 citations· ⚡1
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
