CRITIC-R1 introduces a structured critic framework that treats RAG critique as an explicit error diagnosis problem using reinforcement learning, significantly improving answer quality over strong RAG…

GrepSeek introduces a novel direct corpus interaction (DCI) search agent that trains an LLM to find and compose evidence from large text corpora by issuing executable shell commands, achieving state-o…

LongTraceRL addresses long-context reasoning challenges by generating highly challenging training data and introducing a fine-grained rubric reward, significantly improving evidence-grounded reasoning…

This paper proposes a post-training framework called Retrieval-Augmented Reinforcement Fine-Tuning (RA-RFT) to teach language models to reason by analogy.

The paper proposes MERIT, a dual-level, multi-horizon memory retrieval framework that significantly improves the performance of interactive text-to-SQL agents by providing both global and local memory…

The paper introduces Plan, a structured agentic behavior that decomposes multi-hop questions into ordered sub-questions before retrieval, and proposes a self-bootstrapping paradigm to train it without…

QUBRIC introduces a co-design framework that simultaneously optimizes queries and rubrics, overcoming the bottleneck of vague rubrics derived from open-ended questions, leading to significant gains in…

ExpWeaver introduces a novel framework for LLM agents to learn from past experiences using latent retrieval-augmented generation, achieving state-of-the-art performance while significantly improving t…

This paper introduces cost-aware Retrieval-Augmented Generation (RAG), demonstrating that fixed evidence selection is brittle and that adaptive, agentic controllers are necessary for effective knowled…

SCOPE introduces a data-free self-play framework that co-evolves a task-generating Challenger and a document-answering Solver, significantly improving open-ended performance on language models without…

DynaTree introduces a two-stage framework that pre-constructs a reusable retrieval tree offline using coordinated agents, allowing for efficient, structure-aware, and highly effective time-sensitive n…

SPADER is a novel reinforcement learning framework that addresses the challenges of Multi-Answer Question Answering by improving credit assignment and promoting diverse exploration during long-horizon…

The paper introduces VibeSearchBench, a new benchmark designed to evaluate long-horizon, proactive search capabilities, demonstrating that current state-of-the-art LLM agents are still significantly i…

The paper introduces LinTree, a method that explicitly structures the search history of LLM reasoning traces using parent pointers, significantly improving task performance and search efficiency compa…

The paper argues that current search agents often verify existing knowledge rather than genuinely searching, and introduces LiveBrowseComp, a new benchmark to measure true evidence-driven discovery.

This paper unifies the fragmented field of Tree-of-Thoughts (ToT) reasoning by mapping LLM-based search processes onto a formal taxonomy derived from classical heuristic search theory.

This paper proposes a multi-turn retrieval-augmented generation pipeline for conversational systems across four domains.

The study compares agentic data retrieval using unstructured web data versus structured, semantically-annotated datasets, concluding that semantic metadata remains essential for high-precision, reliab…

The paper introduces AGENTCL, a rigorous evaluation framework that uses controlled task streams to accurately measure an agent's ability to accumulate and reuse knowledge across multiple tasks, thereb…

OmniRetrieval introduces a unified framework that handles natural language queries across diverse, heterogeneous knowledge sources (text, relational, graphs) by dispatching source-native queries witho…