{"total":15,"items":[{"citing_arxiv_id":"2606.23108","ref_index":12,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"TTFT-Aware Graph Chain-of-Thought:Distance-Indexed Neural A* for Low-Hallucination Multi-Hop Medical Reasoning","primary_cat":"cs.AI","submitted_at":"2026-06-22T09:51:28+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"A hybrid PLL oracle and neural A* method constrains LLM generation to paths in a 700K-node medical graph, claiming better latency-recall tradeoffs and fewer hallucinations than text-only RAG on fertility queries.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.20495","ref_index":42,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Increasing Resilience of Continuum Robots via Motion Planning Algorithms","primary_cat":"cs.RO","submitted_at":"2026-06-18T17:10:13+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"Genetic algorithm with AHP produces more diverse paths than A* whose runtime is independent of environment size, claimed to increase continuum robot resilience in two simulated settings.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.08729","ref_index":39,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"IR-SIM: A Lightweight Skill-Native Simulator for Navigation, Learning, and Benchmarking","primary_cat":"cs.RO","submitted_at":"2026-06-07T16:55:37+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"IR-SIM is a YAML-defined simulator for mobile robot navigation that supports text-prompt scenario creation, policy training, benchmarking, and bridging to higher-fidelity or real-world settings.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.06077","ref_index":15,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"3D Underwater Path Planning via Generative Flow Field Surrogates","primary_cat":"cs.RO","submitted_at":"2026-06-04T12:14:59+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"cGAN surrogates recover 45-60% of CFD energy savings and high-velocity wake avoidance in 3D AUV path planning while running at 28-146 microsecond inference speeds across 19,800 trajectories.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.04860","ref_index":4,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Learning Empirically Admissible Neural Heuristics for Combinatorial Search","primary_cat":"cs.LG","submitted_at":"2026-06-03T13:27:46+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Presents a framework for training empirically admissible neural heuristics via underestimating Bellman operator, asymmetric loss, and validation calibration offset, reporting reduced node expansions with no observed admissibility violations on small puzzles.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.01190","ref_index":60,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"The anti-lexicographic SUS-anchor: a near-optimal k=1 sampling scheme","primary_cat":"cs.DS","submitted_at":"2026-05-31T12:11:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"The anti-lexicographic SUS-anchor achieves sampling densities less than 1% above the lower bound for alphabet size 4 and k=1, substantially outperforming bidirectional anchors.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.00990","ref_index":24,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"OSCAR: Obstacle Survival Curves for Adaptive Robot Navigation","primary_cat":"cs.RO","submitted_at":"2026-05-31T04:12:04+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"OSCAR learns class-conditioned survival distributions for obstacle clearance times online (handling right-censored data) to compute patience thresholds in graph-based navigation, converging near oracle performance after few observations per class.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.00315","ref_index":3,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Coupling Language Models with Physics-based Simulation for Synthesis of Inorganic Materials","primary_cat":"cs.AI","submitted_at":"2026-05-29T19:41:29+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A hybrid LLM-plus-physics-simulation framework generates synthesis routes for niobium oxides and finds that LLM implicit priors produce more viable plans than classical path-planning algorithms in computational tests.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.14262","ref_index":19,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Distill: Uncovering the True Intent behind Human-Robot Communication","primary_cat":"cs.RO","submitted_at":"2026-05-14T02:05:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Distill refines user task specifications for robots by pruning unnecessary steps, generalizing meanings, and relaxing order constraints, as demonstrated in a crowdsourcing study on a web interface.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.11117","ref_index":67,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"GRAFT-ATHENA: Self-Improving Agentic Teams for Autonomous Discovery and Evolutionary Numerical Algorithms","primary_cat":"cs.LG","submitted_at":"2026-05-11T18:27:01+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"GRAFT-ATHENA projects combinatorial method choices into factored trees that embed as fingerprints in a metric space, enabling an agentic system to accumulate experience across domains and autonomously discover new numerical techniques for physics-informed problems.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"ability solving, in: MILCOM 2023-2023 IEEE Military Communications Conference (MILCOM), IEEE, 2023, pp. 944-949. [64] M. R. Quillan, Semantic memory, Tech. rep. (1966). [65] A. Newell, H. Simon, The logic theory machine-a complex information processing system, IRE Transactions on information theory 2 (3) (1956) 61-79. [66] A. Newell, A guide to the general problem-solver program gps-2-2, Rand Corporation, 1963. [67] P. E. Hart, N. J. Nilsson, B. Raphael, A formal basis for the heuristic determination of minimum cost paths, IEEE Transactions on Systems Science and Cybernetics 4 (2) (1968) 100-107.doi:10.1109/TSSC.1968.300136. [68] M. Wooldridge, An Introduction to MultiAgent Systems, John Wiley & Sons, Chich- ester, UK, 2002. [69] J. V. Roggeveen, E. Y. Wang, W."},{"citing_arxiv_id":"2604.10587","ref_index":22,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"CogInstrument: Modeling Cognitive Processes for Bidirectional Human-LLM Alignment in Planning Tasks","primary_cat":"cs.HC","submitted_at":"2026-04-12T11:15:18+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"CogInstrument represents human reasoning as revisable cognitive motifs in graphical form to support iterative alignment with LLMs during planning tasks, with a N=12 study indicating gains in targeted revision, agency, and trust over standard dialogue interfaces.","context_count":1,"top_context_role":"method","top_context_polarity":"use_method","context_text":"Each turn is compiled into a small graph patch over an acyclic backbone ofenable,constraint, anddetermineedges, while conflict edges remain explicit outside the backbone so tensions stay inspectable rather than being silently resolved. To keep the graph stable under ongoing revision, singleton-slot candidates are compacted, non-slot concepts are attached with A*-guided anchor selection [22] to preserve local continuity, and cyclic dependencies are detected with Tarjan's algorithm [58] and repaired by remov- ing the weakest structural edge. For presentation, the repaired graph is laid out with a layered strategy inspired by Sugiyama et al. [53], with position stabilization following Brandes and Köpf [5], so recurrent structures remain visually comparable across turns."},{"citing_arxiv_id":"2605.05209","ref_index":252,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Are Flat Minima an Illusion?","primary_cat":"cs.LG","submitted_at":"2026-03-24T06:14:05+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":8.0,"formal_verification":"none","one_line_summary":"Flat minima are illusory; generalization is driven by weakness, a reparameterization-invariant measure of compatible completions that predicts performance better than sharpness on MNIST and Fashion-MNIST.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2601.09634","ref_index":65,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Human Ancestries Simulation and Inference: a Review of Ancestral Recombination Graph-Based Approaches","primary_cat":"q-bio.PE","submitted_at":"2026-01-14T17:09:42+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":2.0,"formal_verification":"none","one_line_summary":"A review of ARG-based simulation and inference methods in population genetics, evaluating their performance, usability, and biological realism with links to software.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2412.13235","ref_index":96,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Logic-Constrained Shortest Paths for Flight Planning","primary_cat":"cs.AI","submitted_at":"2024-12-17T16:18:06+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A branch-and-bound algorithm with custom node selection, branching rules, and conflict definitions solves the logic-constrained shortest path problem for flight planning with traffic flow restrictions, showing order-of-magnitude speedups on a public global dataset with 20000 real constraints.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2305.10601","ref_index":11,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","primary_cat":"cs.CL","submitted_at":"2023-05-17T23:16:17+00:00","verdict":"ACCEPT","verdict_confidence":"HIGH","novelty_score":8.0,"formal_verification":"none","one_line_summary":"Tree of Thoughts enables language models to solve complex planning tasks by generating, evaluating, and searching over coherent intermediate thoughts in a tree, raising Game of 24 success from 4% to 74% with GPT-4.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"end if for s′ ∈ G(pθ, s, k) do ▷ sorted candidates if V (pθ, {s′})(s) > v thres then ▷ pruning DFS(s′, t + 1) end if end for 4. Search algorithm. Finally, within the ToT framework, one can plug and play different search algorithms depending on the tree structure. We explore two relatively simple search algorithms and leave more advanced ones (e.g. A* [11], MCTS [2]) for future work: (a) Breadth-first search (BFS) (Algorithm 1) maintains a set of the b most promising states per step. This is used for Game of 24 and Creative Writing where the tree depth is limit (T ≤ 3), and initial thought steps can be evaluated and pruned to a small set (b ≤ 5). (b) Depth-first search (DFS) (Algorithm 2) explores the most promising state first, until the"}],"limit":50,"offset":0}