τ-Rec is a benchmark for agentic recommender systems with verifiable rewards, RTE mechanism, and pass^k metrics that shows top models reach only ~57% at pass^1 and ~35% at pass^4.
Recbot: Agent-based recommendation system.arXiv preprint arXiv:2509.21317
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5roles
background 1polarities
background 1representative citing papers
SAGER equips LLM recommendation agents with per-user evolving policy skills via two-representation architecture, contrastive CoT diagnosis, and skill-augmented listwise reasoning, yielding SOTA gains orthogonal to memory accumulation.
MARS uses hierarchical event-preference-profile memory with an LLM-scheduled lifecycle of six operations to achieve state-of-the-art results on InstructRec benchmarks.
EvoRec deploys four collaborating LLM agents that co-evolve recommendation models and their optimization methods, reporting up to 5.54% offline gains and 1.85% revenue lift in an online A/B test.
TwiSTAR learns to switch between fast SID retrieval and slow rationale-generating reasoning in generative recommendation, yielding better accuracy-latency trade-offs on three datasets.
citing papers explorer
-
$\tau$-Rec: A Verifiable Benchmark for Agentic Recommender Systems
τ-Rec is a benchmark for agentic recommender systems with verifiable rewards, RTE mechanism, and pass^k metrics that shows top models reach only ~57% at pass^1 and ~35% at pass^4.
-
SAGER: Self-Evolving User Policy Skills for Recommendation Agent
SAGER equips LLM recommendation agents with per-user evolving policy skills via two-representation architecture, contrastive CoT diagnosis, and skill-augmented listwise reasoning, yielding SOTA gains orthogonal to memory accumulation.
-
Agentic Recommender System with Hierarchical Belief-State Memory
MARS uses hierarchical event-preference-profile memory with an LLM-scheduled lifecycle of six operations to achieve state-of-the-art results on InstructRec benchmarks.
-
EvoRec: Self Evolving Agentic Recommender Systems
EvoRec deploys four collaborating LLM agents that co-evolve recommendation models and their optimization methods, reporting up to 5.54% offline gains and 1.85% revenue lift in an online A/B test.
-
TwiSTAR:Think Fast, Think Slow, Then Act,Generative Recommendation with Adaptive Reasoning
TwiSTAR learns to switch between fast SID retrieval and slow rationale-generating reasoning in generative recommendation, yielding better accuracy-latency trade-offs on three datasets.