SIOP enables turn-level credit assignment in LLM agents via semantic clustering of final answers as latent outcomes, improving performance on reasoning benchmarks without verifiers.
hub
and Lewis, Mike , editor =
11 Pith papers cite this work, alongside 152 external citations. Polarity classification is still indexing.
11
Pith papers citing it
152
external citations · Crossref
hub tools
citation-role summary
background 1
dataset 1
citation-polarity summary
representative citing papers
AI Overviews and Gemini retrieve substantially different sources than traditional Google search (Jaccard similarity <0.2), favor Google-owned content, appear for 51.5% of queries especially controversial ones, and are less consistent across repeated or slightly edited queries.
Skill-RAG detects retrieval failure states from hidden representations and routes to one of four corrective skills to raise accuracy on persistent hard cases in open-domain QA and reasoning benchmarks.
Dynamic Gradient Gating monitors lm_head gradient norms to safely reuse rollout batches in RLVR, achieving up to 2.93x sample efficiency and 2.14x wall-clock speedup across math, ALFWorld, WebShop, and QA tasks.
ICRL uses joint RL training of solver and critic with distribution-calibration re-weighting and role-wise advantage estimation to internalize critique into unassisted LLM performance, yielding 6.4-point gains on agentic tasks and 7.0 on math reasoning with Qwen3 models.
Synthetic data improves models only in information-open generation-training loops with external signals, and coarser signals like binary correctness enable better generalization by converging to the most information-efficient component.
Verbal-R3 uses a verbal reranker to generate analytic narratives that guide retrieval and reasoning in LLMs, achieving SOTA results on complex QA benchmarks.
Power-law data sampling creates beneficial asymmetry in the loss landscape that lets models acquire high-frequency skill compositions first, enabling more efficient learning of rare long-tail skills than uniform distributions.
Recurrent-depth transformers achieve systematic generalization and depth extrapolation on implicit reasoning tasks through iterative layer reuse, a three-stage grokking process, and inference-time scaling, while vanilla transformers fail.
ARPO adds entropy-based adaptive rollouts and stepwise advantage attribution to RL for LLM agents, outperforming prior trajectory-level methods on 13 benchmarks with half the tool budget.
citing papers explorer
-
Self-Induced Outcome Potential: Turn-Level Credit Assignment for Agents without Verifiers
SIOP enables turn-level credit assignment in LLM agents via semantic clustering of final answers as latent outcomes, improving performance on reasoning benchmarks without verifiers.
-
How Generative AI Disrupts Search: An Empirical Study of Google Search, Gemini, and AI Overviews
AI Overviews and Gemini retrieve substantially different sources than traditional Google search (Jaccard similarity <0.2), favor Google-owned content, appear for 51.5% of queries especially controversial ones, and are less consistent across repeated or slightly edited queries.
-
Skill-RAG: Failure-State-Aware Retrieval Augmentation via Hidden-State Probing and Skill Routing
Skill-RAG detects retrieval failure states from hidden representations and routes to one of four corrective skills to raise accuracy on persistent hard cases in open-domain QA and reasoning benchmarks.
-
When to Stop Reusing: Dynamic Gradient Gating for Sample-Efficient RLVR
Dynamic Gradient Gating monitors lm_head gradient norms to safely reuse rollout batches in RLVR, achieving up to 2.93x sample efficiency and 2.14x wall-clock speedup across math, ALFWorld, WebShop, and QA tasks.
-
ICRL: Learning to Internalize Self-Critique with Reinforcement Learning
ICRL uses joint RL training of solver and critic with distribution-calibration re-weighting and role-wise advantage estimation to internalize critique into unassisted LLM performance, yielding 6.4-point gains on agentic tasks and 7.0 on math reasoning with Qwen3 models.
-
An Information-Theoretic Criterion for Efficient Data Synthesis
Synthetic data improves models only in information-open generation-training loops with external signals, and coarser signals like binary correctness enable better generalization by converging to the most information-efficient component.
-
Verbal-R3: Verbal Reranker as the Missing Bridge between Retrieval and Reasoning
Verbal-R3 uses a verbal reranker to generate analytic narratives that guide retrieval and reasoning in LLMs, achieving SOTA results on complex QA benchmarks.
-
The Power of Power Law: Asymmetry Enables Compositional Reasoning
Power-law data sampling creates beneficial asymmetry in the loss landscape that lets models acquire high-frequency skill compositions first, enabling more efficient learning of rare long-tail skills than uniform distributions.
-
Loop, Think, & Generalize: Implicit Reasoning in Recurrent-Depth Transformers
Recurrent-depth transformers achieve systematic generalization and depth extrapolation on implicit reasoning tasks through iterative layer reuse, a three-stage grokking process, and inference-time scaling, while vanilla transformers fail.
-
Agentic Reinforced Policy Optimization
ARPO adds entropy-based adaptive rollouts and stepwise advantage attribution to RL for LLM agents, outperforming prior trajectory-level methods on 13 benchmarks with half the tool budget.
- ANCHOR: Abductive Network Construction with Hierarchical Orchestration for Reliable Probability Inference in Large Language Models