Agent-BRACE improves LLM agent performance on long-horizon partially observable tasks by 5.3-14.5% through a decoupled belief state of verbalized atomic claims with certainty labels that keeps context length constant.
hub
Memory as Action: Autonomous Context Curation for Long-Horizon Agentic Tasks
15 Pith papers cite this work. Polarity classification is still indexing.
15
Pith papers citing it
abstract
Long-context Large Language Models, despite their expanded capacity, require careful working memory management to mitigate attention dilution during long-horizon tasks. Yet existing approaches rely on external mechanisms that lack awareness of the agent's reasoning state, leading to suboptimal decisions. We propose Memory-as-Action (MemAct), a framework that treats working memory management as learnable policy actions. By formulating context management as in-place editing operations (deletion, insertion), MemAct enables joint optimization of information retention and task performance through end-to-end reinforcement learning. To address the computational challenges of dynamic context updates, we introduce Dynamic Context Policy Optimization, which restores training efficiency without compromising reasoning integrity. Experiments show that MemAct-RL-14B matches the accuracy of models $16\times$ larger while reducing average context length by 51\%, with learned strategies that adapt to model capabilities and generalize across task complexities.
hub tools
citation-role summary
background 1
baseline 1
citation-polarity summary
representative citing papers
SOLAR is a learning-augmented policy for semantic cache replacement that achieves constant competitive ratio 3 and 5-75% gains over FIFO on retrieval workloads.
OSL-MR is a learning-augmented framework that casts memory retention as constrained stochastic optimization under partial observability and outperforms heuristic baselines on LoCoMo and LongMemEval.
MemMark enables snapshot-only attribution for agent long-term memory by embedding signals via keyed distribution-preserving sampling at memory-write decisions, recovering 40-bit payloads with near-baseline utility.
Memory for long-horizon agents should preserve distinctions that affect decisions under a fixed budget, not descriptive features, yielding an exact forgetting boundary and a new online learner DeMem with regret guarantees.
MemCoE learns memory organization guidelines via contrastive feedback and then trains a guideline-aligned RL policy for memory updates, yielding consistent gains on personalization benchmarks.
ClawVM introduces a harness-managed virtual memory system for LLM agents that ensures deterministic residency and durability of state under token budgets by using typed pages and validated writeback.
PERMA is a new benchmark using temporally ordered events, text variability, and linguistic alignment to evaluate LLM memory agents on persona consistency beyond simple retrieval.
ECHO is a selective turn-memory framework for agentic RL that compresses turns into indexed records, selects them for bounded contexts, and uses source indices to assign outcome credit to supporting evidence, reaching 43.4% accuracy on BrowseComp-Plus versus 28.9% for GRPO and 36.1% for SUPO.
ACE is a pluggable module that elastically orchestrates historical agent steps as raw, abstract, or dropped to maintain compact yet recoverable context for LLM agents handling long trajectories.
HORMA builds a hierarchical memory structure from agent experiences and trains a lightweight RL navigator to retrieve minimal sufficient context, yielding better task performance with at most 22.17% of baseline token usage on ALFWorld, LoCoMo, and LongMemEval.
MemFactory is a new unified modular framework for memory-augmented LLM agent inference and training that integrates GRPO and reports up to 14.8% relative gains on MemAgent evaluations.
Survey that defines agentic RL for LLMs via POMDPs, introduces a taxonomy of planning/tool-use/memory/reasoning capabilities and domains, and compiles open environments from over 500 papers.
ActiveMem proposes a heterogeneous distributed memory framework for LLM agents that separates planning from active memory management, reporting SOTA accuracy with lower overhead on BrowseComp-Plus and GAIA.
Protected policy placements in LLM agents maintain integrity under replay pressure on AutoGen and OpenHands traces, unlike task-local placements which show eviction or weakening.
citing papers explorer
-
Learning What to Remember: Observability-Safe Memory Retention via Constrained Optimization for Long-Horizon Language Agents
OSL-MR is a learning-augmented framework that casts memory retention as constrained stochastic optimization under partial observability and outperforms heuristic baselines on LoCoMo and LongMemEval.
-
Remember the Decision, Not the Description: A Rate-Distortion Framework for Agent Memory
Memory for long-horizon agents should preserve distinctions that affect decisions under a fixed budget, not descriptive features, yielding an exact forgetting boundary and a new online learner DeMem with regret guarantees.
-
ClawVM: Harness-Managed Virtual Memory for Stateful Tool-Using LLM Agents
ClawVM introduces a harness-managed virtual memory system for LLM agents that ensures deterministic residency and durability of state under token budgets by using typed pages and validated writeback.
-
PERMA: Benchmarking Personalized Memory Agents via Event-Driven Preference and Realistic Task Environments
PERMA is a new benchmark using temporally ordered events, text variability, and linguistic alignment to evaluate LLM memory agents on persona consistency beyond simple retrieval.
-
ACE: Pluggable Adaptive Context Elasticizer across Agents
ACE is a pluggable module that elastically orchestrates historical agent steps as raw, abstract, or dropped to maintain compact yet recoverable context for LLM agents handling long trajectories.
-
Organize then Retrieve: Hierarchical Memory Navigation for Efficient Agents
HORMA builds a hierarchical memory structure from agent experiences and trains a lightweight RL navigator to retrieve minimal sufficient context, yielding better task performance with at most 22.17% of baseline token usage on ALFWorld, LoCoMo, and LongMemEval.
-
ActiveMem: Distributed Active Memory for Long-Horizon LLM Reasoning
ActiveMem proposes a heterogeneous distributed memory framework for LLM agents that separates planning from active memory management, reporting SOTA accuracy with lower overhead on BrowseComp-Plus and GAIA.