arXiv:2607. 00233v1 Announce Type: new Abstract: How do two agents invent a shared language from scratch?
arXiv:2607. 08032v1 Announce Type: new Abstract: Large language models, and the agents built on them, spend an ever-growing share of their compute and memory on remembering: caching attention keys and values, carrying long prompts, maintaining recurrent state, and storing what happened in previous turns and sessions.
arXiv:2606. 23195v2 Announce Type: replace Abstract: Large Language Model (LLM) agents increasingly rely on memory systems to maintain long-term coherence.
arXiv:2608. 17053v1 Announce Type: new Abstract: A bounded agent may obtain information for a decision from its own past, from peers, or from both sources.
arXiv:2404. 02039v5 Announce Type: replace Abstract: Game environments provide rich, controllable settings that stimulate many aspects of real-world complexity.
arXiv:2606. 03463v1 Announce Type: new Abstract: Conversational AI agents require memory systems that are both scalable and semantically coherent across long interaction horizons.
arXiv:2606. 08340v1 Announce Type: new Abstract: As language models are increasingly deployed as autonomous agents, they must coordinate with others over long horizons in open-ended interactive tasks.
arXiv:2605. 18421v2 Announce Type: replace-cross Abstract: Recent benchmarks for Large Language Model (LLM) agents mainly evaluate reasoning, planning, and execution.
Large Language Model (LLM) agents increasingly rely on external memory systems to accumulate experience across tasks. Yet nearly all existing approaches, from graph-structured memories to reflective insight stores, access memory through fixed, hand-designed heuristics.
arXiv:2606. 05304v1 Announce Type: new Abstract: Multi-agent systems (MAS) built on large language models are typically organized around roles, pipelines, and turn schedules, while the content that agents pass to one another is often left as unconstrained natural language.
arXiv:2608. 11215v1 Announce Type: new Abstract: Simulating societies of many large language model (LLM) agents is expensive, yet the questions asked of such simulations are usually macroscopic: phase behaviour, stylised facts, and scaling with the number of agents $N$, not the cognition of any single agent.
Large language model (LLM) agents solving multi-step tasks frequently commit to trajectories that are doomed to fail, yet continue to consume substantial inference compute before the failure becomes observable. We show that failure is predictable early from the agent's internal representations: lightweight per-round probes on hidden activations anticipate eventual episode failure as early as the first interaction round, where scorers reading only the agent's observable behavior are barely better than chance.
arXiv:2606. 25115v1 Announce Type: new Abstract: On-device language-model agents improve by accumulating experience in retrieved memory rather than by updating weights.