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…

Critic-R introduces a novel framework that uses a critic model to provide natural language introspective feedback, significantly improving the performance of agentic search systems by optimizing retri…

The paper proposes Deep Research as Rubric (DR-rubric), a novel evidence-driven framework that treats rubric construction itself as a research problem to generate fine-grained, scalable reward signals…

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…

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

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…

The paper introduces TELBench and the DRIFT framework to enable fine-grained, span-level error localization in deep-research agents, significantly improving the ability to pinpoint exactly where an ag…

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…

The paper introduces Contrastive Reflection (CORE), a novel non-parametric method that rapidly improves language model reasoning by distilling contrasts between successful and unsuccessful problem att…

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…

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 Graph-Distance Contribution Reward (GDCR) and Step Advantage Policy Optimization (SAPO) to provide fine-grained, step-level credit assignment for agentic search by modeling world…

The paper introduces TRACE, a novel metric that evaluates the logical structure of LLM reasoning (CoT) by integrating Toulmin's argumentation theory, demonstrating that sound reasoning structure corre…

The paper introduces Chunk-Level Guided Generation, a training-free method that uses an off-the-shelf large language model (LLM) as a process scorer to guide small model generation, achieving performa…

The paper proposes DecomposeR, a planner-centric framework that structures deep research into typed Directed Acyclic Graphs (DAGs) to explicitly improve the planning and execution of large language mo…

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 Loong, a novel human-like agent that significantly improves long document translation by adaptively selecting and utilizing optimal historical context using a specialized memory m…

The paper introduces HRBench, a unified and comprehensive evaluation framework for systematically benchmarking and comparing various thinking-mode switching strategies in hybrid-reasoning LLMs.

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…

This paper investigates how different types of compressed reasoning data (Explicit, Composed, Implicit CoT) affect LLM performance during post-training, finding that the choice of compression and subs…