LoHoSearch is a new benchmark of 544 KG-constructed questions across 11 domains where the strongest search agent scores 34.74% and context strategies add at most 6.8%.
hub Mixed citations
Resum: Unlocking long-horizon search intelligence via context summarization
Mixed citation behavior. Most common role is background (67%).
32
Pith papers citing it
Background
67% of classified citations
hub tools
citation-role summary
background 4
baseline 1
method 1
citation-polarity summary
representative citing papers
The paper proposes Multi-Head Recurrent Memory (MHM) with a select-then-update strategy to improve memory retention in long-context recurrent agents.
ReSum trains LLMs via RLVR to self-summarize reasoning trajectories, yielding 4% average performance gains and 18.6% shorter rollouts through contrastive rollout branches.
VitaBench 2.0 introduces a benchmark for long-term personalized and proactive agent behavior, with results indicating substantial gaps in current frontier LLMs.
Alice uses preservation conflicts from failed candidate updates to create class-stratified hypotheses and guide exploration, improving executable world-model learning under prior misalignment.
MemDocAgent generates consistent hierarchical repository-level code documentation by combining dependency-aware traversal with memory-guided agent interactions that accumulate work traces.
SCOUT achieves state-of-the-art long-text understanding with up to 8x lower token use by actively foraging for sparse query-relevant information and updating a compact provenance-grounded epistemic state.
PlanRAG models natural language exploratory reasoning problems as logical query trees, optimizes them via dynamic programming with a multi-dimensional cost model, and executes iterative retrieval-generation over the trees to outperform prior RAG methods on a new dataset.
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.
VISTA supplies LLM agents with a visible proprioceptive dashboard of typed context blocks, enabling untrained self-management that lifts performance on long-horizon tool-use benchmarks across multiple model scales.
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.
AdaCoM trains an external context manager with RL to improve long-horizon LLM agent performance via adaptive pruning and preservation, revealing a fidelity-reliability trade-off across agents.
RoleMemo dataset and DualMem dual-memory framework let role-playing agents interpret facts through personas, with a 4B model beating larger zero-shot systems on fidelity.
AgentFugue introduces a plug-in shared reasoning hub trained with SFT and RL that enables peer agents to share intermediate reasoning, yielding gains on long-horizon tasks over strong baselines.
SAM is a standalone memory framework for long-horizon LLM agents that creates state-adaptive cues from interactions, preserves raw trajectories for intent-driven recall, and optimizes the module via expert supervision and RL, outperforming baselines on BrowseComp and related benchmarks.
PEEK maintains a constant-sized context map via a programmable cache policy to give LLM agents persistent orientation knowledge about recurring external contexts, yielding 6-34% gains and lower cost than prior prompt-learning methods.
Position-preserving MASK token compression reduces redundancy in diffusion LLMs to accelerate parallel decoding and enable context folding for longer sequences.
Argus coordinates a Navigator and multiple Searchers via an evidence graph for deep research, reporting average gains of 5.5 points with one Searcher and 12.7 points with eight parallel Searchers across eight benchmarks, reaching 86.2 on BrowseComp with 64 Searchers.
PRISM is a new inference-time retrieval system that achieves higher accuracy than baselines on long-horizon agent tasks while using an order of magnitude less context by combining hierarchical graph search, intent-based costing, compression, and adaptive routing over structured memory.
Slipstream uses asynchronous compaction with trajectory-grounded judge validation to improve long-horizon agent accuracy by up to 8.8 percentage points and reduce latency by up to 39.7%.
A large model generates a compact reasoning signal that a small model uses to solve tasks, reducing the large model's output tokens by up to 60% on benchmarks like AIME and GPQA.
LMM-Searcher uses file-based visual UIDs and a fetch tool plus 12K synthesized trajectories to fine-tune a multimodal agent that scales to 100-turn horizons and reaches SOTA among open-source models on MM-BrowseComp and MMSearch-Plus.
AggAgent uses an agent with inspection tools to aggregate parallel trajectories for agentic tasks, outperforming prior methods by up to 5.3% on average across benchmarks.
citing papers explorer
-
ReSum: Synergizing LLM Reasoning and Summarization with Reinforcement Learning
ReSum trains LLMs via RLVR to self-summarize reasoning trajectories, yielding 4% average performance gains and 18.6% shorter rollouts through contrastive rollout branches.
-
VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactions
VitaBench 2.0 introduces a benchmark for long-term personalized and proactive agent behavior, with results indicating substantial gaps in current frontier LLMs.
-
Baba in Wonderland: Online Self-Supervised Dynamics Discovery for Executable World Models
Alice uses preservation conflicts from failed candidate updates to create class-stratified hypotheses and guide exploration, improving executable world-model learning under prior misalignment.
-
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.
-
Learning Agent-Compatible Context Management for Long-Horizon Tasks
AdaCoM trains an external context manager with RL to improve long-horizon LLM agent performance via adaptive pruning and preservation, revealing a fidelity-reliability trade-off across agents.
-
AgentFugue: Agent Scaling for Long-Horizon Tasks through Collective Reasoning
AgentFugue introduces a plug-in shared reasoning hub trained with SFT and RL that enables peer agents to share intermediate reasoning, yielding gains on long-horizon tasks over strong baselines.
-
SAM: State-Adaptive Memory for Long-Horizon Reasoning Agent
SAM is a standalone memory framework for long-horizon LLM agents that creates state-adaptive cues from interactions, preserves raw trajectories for intent-driven recall, and optimizes the module via expert supervision and RL, outperforming baselines on BrowseComp and related benchmarks.
-
PEEK: Context Map as an Orientation Cache for Long-Context LLM Agents
PEEK maintains a constant-sized context map via a programmable cache policy to give LLM agents persistent orientation knowledge about recurring external contexts, yielding 6-34% gains and lower cost than prior prompt-learning methods.
-
MEMENTO: Teaching LLMs to Manage Their Own Context
MEMENTO trains LLMs to segment reasoning into blocks, generate mementos as dense summaries, and reason forward using only mementos and KV states, cutting peak KV cache by ~2.5x while preserving benchmark accuracy.
-
The Landscape of Agentic Reinforcement Learning for LLMs: A Survey
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: 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.
-
Enhancing Multi-Agent Communication through Attention Steering with Context Relevance
Agent-Radar is a training-free context management technique applying temporal and spatial decay to focus multi-agent LLM attention on relevant history, delivering up to 7.64 point gains on five benchmarks.