RecRM-Bench is a new large-scale benchmark dataset and framework for multi-dimensional reward modeling in agentic recommender systems, spanning instruction following, factual consistency, query-item relevance, and user behavior prediction.
Initialization with Forced Diversifi- cation
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
citation-role summary
background 4
citation-polarity summary
years
2026 12roles
background 4polarities
background 4representative citing papers
SubSearch improves LLM reasoning traces on QA and multi-hop QA tasks by rewarding intermediate steps with intrinsic process rewards instead of only final outcomes.
ReSum's contrastive RL branching on self-summarization points improves LLM math reasoning accuracy by about 4% and shortens rollouts by about 18.6% across tested backbones.
Bits-over-Random (BoR) is a chance-corrected metric for tool shortlist evaluation that enables query-adaptive depth selection via RL, matching fixed-list coverage with shorter lists on BFCL and ToolBench.
RSCB-MC is a risk-sensitive contextual bandit memory controller for LLM coding agents that chooses safe actions including abstention, achieving 60.5% proxy success with 0% false positives and low latency in 200-case validation.
MemSearch-o1 mitigates memory dilution in agentic LLM search through reasoning-aligned token-level memory growth, retracing with a contribution function, and path reorganization, improving reasoning activation on benchmarks.
OASES co-trains a search policy and an outcome-aligned state evaluator so intermediate search steps get denser, outcome-consistent process rewards and beat strong RL baselines on multi-hop QA.
Gome reaches 35.1% any-medal rate on MLE-Bench by mapping reasoning to gradient-based updates, outperforming tree search once models are sufficiently capable.
This survey categorizes agentic environments for LLMs by eight attributes and domains, introduces symbolic and neural synthesis paradigms with evaluation, and outlines four agent evolution pathways plus three environment evolution paradigms.
PDR is a user-context-aware framework for LLM research agents that improves report relevance over static baselines, supported by a new dataset and hybrid evaluation.
R²-Searcher introduces fine-grained evidence modeling, retrieval reflection, and R²PO RL to calibrate retrieval-reasoning boundaries and improve multi-hop QA performance.
citing papers explorer
-
RecRM-Bench: Benchmarking Multidimensional Reward Modeling for Agentic Recommender Systems
RecRM-Bench is a new large-scale benchmark dataset and framework for multi-dimensional reward modeling in agentic recommender systems, spanning instruction following, factual consistency, query-item relevance, and user behavior prediction.
-
SubSearch: Intermediate Rewards for Unsupervised Guided Reasoning in Complex Retrieval
SubSearch improves LLM reasoning traces on QA and multi-hop QA tasks by rewarding intermediate steps with intrinsic process rewards instead of only final outcomes.
-
ReSum: Synergizing LLM Reasoning and Summarization with Reinforcement Learning
ReSum's contrastive RL branching on self-summarization points improves LLM math reasoning accuracy by about 4% and shortens rollouts by about 18.6% across tested backbones.
-
How Many Tools Should an LLM Agent See? A Chance-Corrected Answer
Bits-over-Random (BoR) is a chance-corrected metric for tool shortlist evaluation that enables query-adaptive depth selection via RL, matching fixed-list coverage with shorter lists on BFCL and ToolBench.
-
Learning When to Remember: Risk-Sensitive Contextual Bandits for Abstention-Aware Memory Retrieval in LLM-Based Coding Agents
RSCB-MC is a risk-sensitive contextual bandit memory controller for LLM coding agents that chooses safe actions including abstention, achieving 60.5% proxy success with 0% false positives and low latency in 200-case validation.
-
MemSearch-o1: Empowering Large Language Models with Reasoning-Aligned Memory Growth in Agentic Search
MemSearch-o1 mitigates memory dilution in agentic LLM search through reasoning-aligned token-level memory growth, retracing with a contribution function, and path reorganization, improving reasoning activation on benchmarks.
-
OASES: Outcome-Aligned Search-Evaluation Co-Training for Agentic Search
OASES co-trains a search policy and an outcome-aligned state evaluator so intermediate search steps get denser, outcome-consistent process rewards and beat strong RL baselines on multi-hop QA.
-
Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search
Gome reaches 35.1% any-medal rate on MLE-Bench by mapping reasoning to gradient-based updates, outperforming tree search once models are sufficiently capable.
-
Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application
This survey categorizes agentic environments for LLMs by eight attributes and domains, introduces symbolic and neural synthesis paradigms with evaluation, and outlines four agent evolution pathways plus three environment evolution paradigms.
-
Personalized Deep Research: A User-Centric Framework, Dataset, and Hybrid Evaluation for Knowledge Discovery
PDR is a user-context-aware framework for LLM research agents that improves report relevance over static baselines, supported by a new dataset and hybrid evaluation.
-
R$^2$-Searcher: Calibrating Retrieval and Reasoning Boundaries for Agentic Search
R²-Searcher introduces fine-grained evidence modeling, retrieval reflection, and R²PO RL to calibrate retrieval-reasoning boundaries and improve multi-hop QA performance.
- CuSearch: Curriculum Rollout Sampling via Search Depth for Agentic RAG