MedMemoryBench supplies a 2,000-session synthetic medical trajectory dataset and an evaluate-while-constructing streaming protocol to expose memory saturation and reasoning failures in current agent architectures for personalized healthcare.
citation dossier
Memagent: Reshaping long-context llm with multi-conv rl-based memory agent
17Pith papers citing it
17reference links
cs.AItop field · 6 papers
UNVERDICTEDtop verdict bucket · 15 papers
why this work matters in Pith
Pith has found this work in 17 reviewed papers. Its strongest current cluster is cs.AI (6 papers). The largest review-status bucket among citing papers is UNVERDICTED (15 papers). For highly cited works, this page shows a dossier first and a bounded explorer second; it never tries to render every citing paper at once.
years
2026 17representative citing papers
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.
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.
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.
PRIME enables agents to proactively reason in user-centric tasks by iteratively evolving structured memories from interaction trajectories without gradient-based training.
Context-ReAct enables agents to dynamically manage context via five atomic operations, and LongSeeker fine-tuned on 10k trajectories achieves 61.5% and 62.5% on BrowseComp benchmarks, outperforming prior agents.
Metadata Reasoner uses agentic LLM reasoning on metadata to select sufficient and minimal data sources, achieving 83.16% F1 on KramaBench and 85.5% F1 on noisy synthetic benchmarks while avoiding low-quality tables 99% of the time.
POINTS-Seeker-8B is an 8B multimodal model trained from scratch for agentic search that uses seeding and visual-space history folding to outperform prior models on six visual reasoning benchmarks.
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.
In-Place TTT adapts LLM MLP projection matrices at test time with a next-token-aligned objective and chunk-wise updates, enabling better long-context performance as a drop-in enhancement.
Decocted experience—extracting and organizing the essence from accumulated interactions—enables more effective context construction that improves test-time inference in LLM agents on math, web, and software tasks.
LightThinker++ adds explicit adaptive memory management and a trajectory synthesis pipeline to LLM reasoning, cutting peak token use by ~70% while gaining accuracy in standard and long-horizon agent tasks.
GrandCode is the first AI system to consistently beat all human participants and place first in live Codeforces competitive programming contests.
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.
MiA-Signature approximates the global activation state induced by a query via submodular concept selection to enable tractable long-context understanding in LLMs.
LongAct uses saliency from high-magnitude activations to guide sparse weight updates in long-context RL, yielding about 8% gains on LongBench v2 across multiple algorithms.
Unifying LLM memory optimizations into a Prepare-Compute-Retrieve-Apply pipeline and accelerating it on GPU-FPGA hardware yields up to 2.2x faster inference and 4.7x less energy than GPU-only baselines.
citing papers explorer
-
MedMemoryBench: Benchmarking Agent Memory in Personalized Healthcare
MedMemoryBench supplies a 2,000-session synthetic medical trajectory dataset and an evaluate-while-constructing streaming protocol to expose memory saturation and reasoning failures in current agent architectures for personalized healthcare.
-
Agent-BRACE: Decoupling Beliefs from Actions in Long-Horizon Tasks via Verbalized State Uncertainty
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.
-
SCOUT: Active Information Foraging for Long-Text Understanding with Decoupled Epistemic States
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.
-
Learning How and What to Memorize: Cognition-Inspired Two-Stage Optimization for Evolving Memory
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.
-
PRIME: Training Free Proactive Reasoning via Iterative Memory Evolution for User-Centric Agent
PRIME enables agents to proactively reason in user-centric tasks by iteratively evolving structured memories from interaction trajectories without gradient-based training.
-
LongSeeker: Elastic Context Orchestration for Long-Horizon Search Agents
Context-ReAct enables agents to dynamically manage context via five atomic operations, and LongSeeker fine-tuned on 10k trajectories achieves 61.5% and 62.5% on BrowseComp benchmarks, outperforming prior agents.
-
An Agentic Approach to Metadata Reasoning
Metadata Reasoner uses agentic LLM reasoning on metadata to select sufficient and minimal data sources, achieving 83.16% F1 on KramaBench and 85.5% F1 on noisy synthetic benchmarks while avoiding low-quality tables 99% of the time.
-
POINTS-Seeker: Towards Training a Multimodal Agentic Search Model from Scratch
POINTS-Seeker-8B is an 8B multimodal model trained from scratch for agentic search that uses seeding and visual-space history folding to outperform prior models on six visual reasoning benchmarks.
-
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.
-
In-Place Test-Time Training
In-Place TTT adapts LLM MLP projection matrices at test time with a next-token-aligned objective and chunk-wise updates, enabling better long-context performance as a drop-in enhancement.
-
Decocted Experience Improves Test-Time Inference in LLM Agents
Decocted experience—extracting and organizing the essence from accumulated interactions—enables more effective context construction that improves test-time inference in LLM agents on math, web, and software tasks.
-
LightThinker++: From Reasoning Compression to Memory Management
LightThinker++ adds explicit adaptive memory management and a trajectory synthesis pipeline to LLM reasoning, cutting peak token use by ~70% while gaining accuracy in standard and long-horizon agent tasks.
-
GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning
GrandCode is the first AI system to consistently beat all human participants and place first in live Codeforces competitive programming contests.
-
MemFactory: Unified Inference & Training Framework for Agent Memory
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.
-
MiA-Signature: Approximating Global Activation for Long-Context Understanding
MiA-Signature approximates the global activation state induced by a query via submodular concept selection to enable tractable long-context understanding in LLMs.
-
LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning
LongAct uses saliency from high-magnitude activations to guide sparse weight updates in long-context RL, yielding about 8% gains on LongBench v2 across multiple algorithms.
-
Understand and Accelerate Memory Processing Pipeline for Disaggregated LLM Inference
Unifying LLM memory optimizations into a Prepare-Compute-Retrieve-Apply pipeline and accelerating it on GPU-FPGA hardware yields up to 2.2x faster inference and 4.7x less energy than GPU-only baselines.